© 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 Local
    9. 6-RES_SCL-AJT
    11. 35360
    Prev
    Next
    INDEX
    Explanations

    mentions of the American Civil Liberties Union (ACLU) and related concepts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.18
    1.0%
    288
    +0.14
    0.8%
    343
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.18
    0.27
    267
    +0.14
    0.09
    145
    +0.10
    0.06
    Negative Logits
    rule
    -0.66
    lasses
    -0.59
    lass
    -0.57
    history
    -0.56
    uled
    -0.56
    xit
    -0.56
    hots
    -0.54
    abiding
    -0.53
    oters
    -0.53
    seys
    -0.52
    POSITIVE LOGITS
     Fein
    0.74
    uthor
    0.63
     Horowitz
    0.62
     ACLU
    0.60
    OC
    0.58
     Liberties
    0.58
    REAM
    0.57
     Greenwald
    0.56
    IG
    0.56
    UTH
    0.55
    Activations Density 11.261%

    No Known Activations