© 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 EvalsExportsinterp-engineNEWAPI 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. 7292
    Prev
    Next
    INDEX
    Explanations

    Go code snippets showing defining and using functions

    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
    545
    +0.16
    0.6%
    27
    +0.16
    0.5%
    211
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    545
    +0.16
    0.02
    326
    +0.16
    0.02
    683
    +0.14
    0.02
    Negative Logits
    yss
    -1.08
    gdala
    -1.03
    alus
    -1.00
     GOODMAN
    -0.98
    achus
    -0.95
     Frie
    -0.93
    ngth
    -0.93
    ocene
    -0.92
    enery
    -0.92
    swer
    -0.89
    POSITIVE LOGITS
    iona
    1.06
     func
    1.04
    uto
    0.99
    func
    0.98
    (*
    0.98
    oses
    0.95
    ests
    0.94
    emic
    0.91
    inces
    0.90
    iton
    0.86
    Activations Density 0.139%

    No Known Activations