© 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. 18812
    Prev
    Next
    INDEX
    Explanations

    historical anecdotes and facts

    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
    650
    +0.11
    0.5%
    598
    +0.10
    0.5%
    723
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.11
    0.07
    650
    +0.10
    0.05
    512
    +0.10
    0.05
    Negative Logits
    iates
    -0.71
    ventures
    -0.66
    iate
    -0.63
    ationally
    -0.61
     occas
    -0.60
    atures
    -0.60
    bowl
    -0.60
    ogun
    -0.60
    imeters
    -0.59
    zon
    -0.59
    POSITIVE LOGITS
     nil
    0.79
     elusive
    0.78
     namely
    0.71
    \\\\\\\\
    0.70
    cule
    0.70
     none
    0.69
     nowhere
    0.68
     undoubtedly
    0.66
    \-
    0.65
    abella
    0.65
    Activations Density 0.213%

    No Known Activations