© 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. 12245
    Prev
    Next
    INDEX
    Explanations

    information related to skill specialization, training, learning, and expertise in various fields

    oai_token-act-pair · gpt-3.5-turbo
    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
    640
    +0.35
    2.2%
    160
    +0.11
    0.7%
    107
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.35
    0.32
    442
    +0.11
    0.22
    160
    +0.08
    0.24
    Negative Logits
     lifes
    -0.61
     commission
    -0.60
     undet
    -0.59
     legally
    -0.54
     sacked
    -0.54
     receiving
    -0.54
     censored
    -0.53
     veter
    -0.53
     administr
    -0.53
     appe
    -0.53
    POSITIVE LOGITS
    Conclusion
    1.02
    Finally
    0.96
    Lastly
    0.94
    Moreover
    0.92
    Advertisements
    0.91
    However
    0.91
    Meanwhile
    0.91
    Examples
    0.91
    Similarly
    0.90
    Since
    0.90
    Activations Density 1.412%

    No Known Activations