© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10209
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters and regulations

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    450
    +0.12
    0.5%
    489
    +0.12
    0.4%
    215
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.04
    181
    +0.12
    0.04
    326
    +0.12
    0.04
    Negative Logits
     Darius
    -0.88
    DERR
    -0.84
    >>\
    -0.83
    riots
    -0.80
    ahime
    -0.79
    ahu
    -0.78
    ians
    -0.78
     Miranda
    -0.78
    onso
    -0.78
     Saban
    -0.77
    POSITIVE LOGITS
    pload
    1.17
    pling
    1.07
    uler
    1.05
    wed
    0.96
    pel
    0.96
    ggle
    0.94
    reenshots
    0.94
    eding
    0.91
    arer
    0.91
    pled
    0.91
    Activations Density 0.254%

    No Known Activations