© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 4187
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action or change

    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
    281
    +0.10
    0.5%
    118
    +0.09
    0.4%
    237
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.10
    0.07
    70
    +0.09
    0.06
    351
    +0.09
    0.04
    Negative Logits
     equally
    -0.69
     aptly
    -0.67
     specifically
    -0.66
     curiously
    -0.64
     chiefly
    -0.63
     optionally
    -0.63
     generally
    -0.62
     distinctly
    -0.61
    usually
    -0.61
     oddly
    -0.60
    POSITIVE LOGITS
    ãĥīãĥ©
    0.84
    arded
    0.80
    ifiable
    0.77
    Initialized
    0.76
    enance
    0.76
    rencies
    0.71
    yth
    0.67
    ounters
    0.67
    hing
    0.65
    uga
    0.65
    Activations Density 0.533%

    No Known Activations