© 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. 33786
    Prev
    Next
    INDEX
    Explanations

    phrases related to voting and political endorsements

    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
    +0.30
    1.6%
    78
    +0.11
    0.6%
    385
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.30
    0.24
    362
    +0.11
    0.12
    608
    +0.10
    0.17
    Negative Logits
    ngth
    -0.86
    illin
    -0.76
    Scope
    -0.72
    urst
    -0.70
    clair
    -0.68
    mone
    -0.67
    icult
    -0.64
    urgical
    -0.61
    edin
    -0.60
    WARN
    -0.60
    POSITIVE LOGITS
     whichever
    0.75
     captcha
    0.72
     reelection
    0.70
     Hillary
    0.69
     starters
    0.68
     whatever
    0.68
     hire
    0.65
    geries
    0.65
     whoever
    0.65
     politicians
    0.64
    Activations Density 9.380%

    No Known Activations