© 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. 17586
    Prev
    Next
    INDEX
    Explanations

    words related to written works and literary analysis

    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
    447
    +0.17
    0.8%
    558
    +0.11
    0.5%
    542
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    542
    +0.17
    0.05
    56
    +0.11
    0.04
    540
    +0.10
    0.05
    Negative Logits
    ogenesis
    -0.76
    foreseen
    -0.73
    prefix
    -0.72
    undreds
    -0.69
    anamo
    -0.68
    suff
    -0.68
    uez
    -0.66
    ivably
    -0.66
    iliated
    -0.66
    termination
    -0.66
    POSITIVE LOGITS
     versatile
    1.01
     Helpful
    0.93
     underrated
    0.88
     informative
    0.84
     masterpiece
    0.84
     enjoyable
    0.82
     opener
    0.81
     superb
    0.81
     excellent
    0.81
     puzzle
    0.80
    Activations Density 0.318%

    No Known Activations