© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19979
    Prev
    Next
    INDEX
    Explanations

    words related to actions or processes that involve ongoing or continuous movement or development

    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
    314
    +0.17
    0.8%
    128
    +0.12
    0.6%
    739
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.04
    314
    +0.12
    0.01
    288
    +0.11
    0.04
    Negative Logits
    ULTS
    -0.69
     Nare
    -0.69
     brim
    -0.66
    CHR
    -0.63
     reper
    -0.63
    vae
    -0.60
    omez
    -0.59
    ULT
    -0.57
    SPONSORED
    -0.57
     deaf
    -0.56
    POSITIVE LOGITS
    ing
    2.61
    ership
    1.39
    edIn
    1.31
    ed
    1.29
    ING
    1.26
    er
    1.15
    ingham
    1.13
    ington
    1.10
    ingo
    1.03
    ings
    1.01
    Activations Density 0.135%

    No Known Activations