© 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. 2831
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or accusations

    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
    393
    +0.14
    0.6%
    458
    +0.12
    0.5%
    549
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.14
    0.15
    526
    +0.12
    0.00
    549
    +0.11
    0.09
    Negative Logits
    soDeliveryDate
    -1.30
    SourceFile
    -0.95
    tions
    -0.89
    inventoryQuantity
    -0.87
    OVER
    -0.82
    paren
    -0.81
    agogue
    -0.80
    soType
    -0.80
    tek
    -0.79
    natureconservancy
    -0.79
    POSITIVE LOGITS
    erous
    1.24
     unsuspecting
    1.20
     behalf
    1.19
     civilians
    1.06
     innocent
    1.01
     him
    0.98
     anyone
    0.96
    etime
    0.92
     oneself
    0.92
     anybody
    0.90
    Activations Density 2.984%

    No Known Activations