© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39763
    Prev
    Next
    INDEX
    Explanations

    information related to political committees and investigations

    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
    476
    +0.10
    0.5%
    447
    +0.10
    0.5%
    650
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.22
    430
    +0.10
    0.16
    330
    +0.09
    0.07
    Negative Logits
    à¨
    -0.70
    ãĤ¨ãĥ«
    -0.69
    zsche
    -0.69
     Kop
    -0.67
    iewicz
    -0.66
     à¨
    -0.66
    gra
    -0.65
    íķ
    -0.63
    spr
    -0.63
     Haf
    -0.63
    POSITIVE LOGITS
     Subcommittee
    1.00
     hearings
    0.91
     subcommittee
    0.85
     subpoen
    0.85
    sylvania
    0.84
     Inquiry
    0.84
     congressional
    0.84
     Appropriations
    0.84
    essee
    0.83
     Investigative
    0.83
    Activations Density 9.286%

    No Known Activations