© 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. 18810
    Prev
    Next
    INDEX
    Explanations

    numerical quantities mentioned in a context of statistics or measurements

    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
    480
    +0.45
    2.5%
    36
    +0.24
    1.3%
    393
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.45
    0.24
    250
    +0.24
    0.10
    328
    +0.17
    0.09
    Negative Logits
    evidence
    -0.63
     Vaugh
    -0.61
    sheets
    -0.60
    grounds
    -0.60
    iments
    -0.59
    agree
    -0.58
    onto
    -0.58
    Edit
    -0.57
    Enter
    -0.56
     accordingly
    -0.56
    POSITIVE LOGITS
     lot
    1.00
     bunch
    0.89
     whopping
    0.76
     handful
    0.76
     couple
    0.76
    uras
    0.76
     few
    0.75
     glimpse
    0.74
    sexual
    0.74
     huge
    0.73
    Activations Density 0.539%

    No Known Activations