© 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. 36771
    Prev
    Next
    INDEX
    Explanations

    references to civil liberties and government control in politics and society

    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
    +0.16
    0.9%
    288
    +0.12
    0.7%
    575
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.16
    0.13
    546
    +0.12
    0.07
    90
    +0.10
    0.07
    Negative Logits
    gaard
    -0.64
    BY
    -0.61
    HEAD
    -0.59
     Cosponsors
    -0.58
    soDeliveryDate
    -0.57
    PM
    -0.56
    outed
    -0.55
    ERO
    -0.54
    Production
    -0.53
    OUT
    -0.53
    POSITIVE LOGITS
     liberties
    0.82
     Liberties
    0.79
     freedoms
    0.74
     entitle
    0.66
    fulness
    0.65
    Thumbnail
    0.65
     rights
    0.64
     liberty
    0.64
    tarian
    0.64
     afforded
    0.62
    Activations Density 6.288%

    No Known Activations