© 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 12288
    9. 8-RES_FS12288-JB
    11. 701
    Prev
    Next
    INDEX
    Explanations

    descriptions of locations or events involving a community

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    344
    +0.12
    0.5%
    626
    +0.11
    0.5%
    700
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.12
    0.04
    626
    +0.11
    0.04
    700
    +0.10
    0.04
    Negative Logits
    friends
    -0.77
    none
    -0.74
    KER
    -0.73
    cs
    -0.72
    chairs
    -0.68
    acons
    -0.66
    rants
    -0.65
    killers
    -0.65
    olas
    -0.64
    Dr
    -0.64
    POSITIVE LOGITS
    heartedly
    1.07
    hearted
    1.07
     ordeal
    1.02
     thing
    1.00
     globe
    0.98
     gam
    0.95
     spectrum
    0.95
     continent
    0.88
     ecosystem
    0.88
     affair
    0.85
    Activations Density 0.063%

    No Known Activations