© 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. 35449
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent events and political activism

    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
    498
    +0.09
    0.4%
    345
    +0.09
    0.4%
    304
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.09
    0.07
    608
    +0.09
    0.14
    370
    +0.09
    0.04
    Negative Logits
    luaj
    -0.72
    acha
    -0.69
    inance
    -0.67
    sleep
    -0.66
    ophon
    -0.65
    lean
    -0.63
    isl
    -0.62
    elo
    -0.62
    ult
    -0.61
    isd
    -0.61
    POSITIVE LOGITS
    -->
    0.78
     scratching
    0.74
     scratches
    0.74
     sympt
    0.69
     frontier
    0.69
     collateral
    0.67
     stim
    0.65
    .............
    0.64
    ----
    0.63
     facet
    0.63
    Activations Density 9.521%

    No Known Activations