© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 7596
    Prev
    Next
    INDEX
    Explanations

    words related to opinions or beliefs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.20
    1.0%
    334
    +0.13
    0.6%
    57
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.20
    0.03
    306
    +0.13
    0.03
    373
    +0.12
    -0.01
    Negative Logits
    "},"
    -0.75
    etter
    -0.63
    artney
    -0.62
    natureconservancy
    -0.62
    ropolis
    -0.62
    rosis
    -0.61
    DN
    -0.61
    debian
    -0.60
    dL
    -0.60
    uits
    -0.59
    POSITIVE LOGITS
     yourselves
    0.72
     yours
    0.71
    beit
    0.69
    ably
    0.69
     kidding
    0.66
     me
    0.66
     guessing
    0.63
    ingly
    0.62
    fax
    0.62
     thy
    0.62
    Activations Density 0.114%

    No Known Activations