© 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. 10456
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal/criminal activities and prison sentences

    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
    250
    +0.07
    0.5%
    610
    +0.07
    0.5%
    108
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.07
    0.01
    160
    +0.07
    0.01
    486
    +0.07
    0.01
    Negative Logits
    strip
    -0.46
    uel
    -0.46
    rs
    -0.45
    estone
    -0.43
    email
    -0.43
    HEAD
    -0.43
    Bloom
    -0.42
    ull
    -0.42
     il
    -0.42
    tail
    -0.42
    POSITIVE LOGITS
     withd
    0.61
     mosqu
    0.56
    senal
    0.50
     Nieto
    0.47
     Parenthood
    0.47
    ©¶æ
    0.46
     cannibal
    0.45
     Prosecut
    0.45
    ô
    0.44
     advoc
    0.44
    Activations Density 0.026%

    No Known Activations