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

    Neuronpedia

    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. 7920
    Prev
    Next
    INDEX
    Explanations

    words related to cause and effect or consequences

    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
    679
    +0.13
    0.6%
    208
    +0.11
    0.5%
    333
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.13
    0.02
    403
    +0.11
    0.02
    460
    +0.10
    0.02
    Negative Logits
     Vaugh
    -0.67
    anus
    -0.65
    vae
    -0.65
    rones
    -0.62
    tera
    -0.62
    arag
    -0.62
    nan
    -0.61
    pent
    -0.59
    estern
    -0.58
    zan
    -0.57
    POSITIVE LOGITS
     thereof
    0.83
    ãĤ¯
    0.75
    forth
    0.74
     of
    0.71
    ,...
    0.68
    alion
    0.62
    ,.
    0.62
    ,
    0.61
     there
    0.60
    ainer
    0.58
    Activations Density 0.018%

    No Known Activations