© 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. 999
    Prev
    Next
    INDEX
    Explanations

    verbs related to proving, verifying, or determining something, especially in the context of evidence or facts

    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
    351
    +0.14
    0.5%
    288
    +0.12
    0.4%
    611
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.14
    0.06
    195
    +0.12
    0.02
    610
    +0.12
    0.04
    Negative Logits
    ummer
    -1.06
    cffffcc
    -1.00
    alez
    -0.94
     liner
    -0.94
    catentry
    -0.94
    ishops
    -0.84
     contrace
    -0.84
    EStreamFrame
    -0.83
    phrine
    -0.83
    umbn
    -0.81
    POSITIVE LOGITS
    biz
    1.02
    reader
    1.00
    iary
    0.97
    manship
    0.97
    proof
    0.97
    poses
    0.94
    \\\\\\\\
    0.92
     proof
    0.92
    ifications
    0.92
    heet
    0.91
    Activations Density 0.916%

    No Known Activations