© 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. 35759
    Prev
    Next
    INDEX
    Explanations

    political parties and related terms, particularly focusing on the Conservative Party

    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
    +0.11
    0.5%
    130
    +0.10
    0.5%
    17
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.18
    527
    +0.10
    0.04
    442
    +0.09
    0.07
    Negative Logits
    anwhile
    -0.86
    icter
    -0.77
    ilation
    -0.75
    ius
    -0.73
    ipt
    -0.72
    othing
    -0.71
    olean
    -0.69
    ensitive
    -0.68
    orative
    -0.68
    uations
    -0.67
    POSITIVE LOGITS
     Party
    0.89
     MPs
    0.77
    Home
    0.77
     Parties
    0.64
     MP
    0.64
    Party
    0.63
     ministers
    0.63
     cabinet
    0.63
     Political
    0.61
     parliamentary
    0.60
    Activations Density 7.320%

    No Known Activations