© 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. 12857
    Prev
    Next
    INDEX
    Explanations

    chemical elements and compounds

    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
    +0.33
    1.2%
    393
    +0.17
    0.6%
    160
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.33
    0.14
    160
    +0.17
    0.14
    314
    +0.17
    0.02
    Negative Logits
     semblance
    -0.99
     absor
    -0.98
    olicy
    -0.97
     lodging
    -0.93
     appropri
    -0.93
     footing
    -0.93
     minded
    -0.92
     inund
    -0.92
     spir
    -0.91
     extrater
    -0.91
    POSITIVE LOGITS
    âĢ¦)
    1.74
    ...)
    1.55
    emphasis
    1.53
    laughs
    1.53
    Laughs
    1.42
    sic
    1.40
    ++)
    1.34
    See
    1.34
    Especially
    1.34
    Note
    1.26
    Activations Density 1.632%

    No Known Activations