© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 357
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and legal terms related to criminal cases

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or specific names, particularly those related to organizations, places, or key individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    326
    +0.22
    0.8%
    288
    +0.17
    0.6%
    618
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.22
    0.15
    232
    +0.17
    0.12
    659
    +0.12
    0.12
    Negative Logits
    ×Ļ×
    -1.06
    ãĥīãĥ©ãĤ´ãĥ³
    -0.91
    ×Ļ
    -0.91
    è¡
    -0.90
    advertisement
    -0.90
    使
    -0.84
    ãĥŁ
    -0.82
    ************
    -0.80
     à¨
    -0.80
    pron
    -0.80
    POSITIVE LOGITS
    acles
    0.95
    opa
    0.92
    oslav
    0.91
    quet
    0.89
    sten
    0.87
    raine
    0.86
    erity
    0.86
    eto
    0.86
    ney
    0.86
    forth
    0.85
    Activations Density 3.769%

    No Known Activations