© 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. 19733
    Prev
    Next
    INDEX
    Explanations

    references to people holding positions or titles in a professional or organizational setting

    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
    +0.16
    0.8%
    314
    +0.13
    0.6%
    232
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.16
    0.03
    232
    +0.13
    0.03
    659
    +0.10
    0.03
    Negative Logits
    paces
    -0.71
     pleas
    -0.69
     tumble
    -0.69
    CRIP
    -0.68
     warranty
    -0.67
     deed
    -0.65
     lumber
    -0.62
    IGHTS
    -0.61
     alt
    -0.60
     ABE
    -0.60
    POSITIVE LOGITS
    assian
    1.13
    hart
    0.99
    entin
    0.98
    ayne
    0.89
    idon
    0.88
    inal
    0.85
    aign
    0.85
    ston
    0.84
    elia
    0.84
    rick
    0.84
    Activations Density 0.085%

    No Known Activations