© 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. 1304
    Prev
    Next
    INDEX
    Explanations

    phrases introducing a new or important topic

    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
    702
    +0.11
    0.5%
    274
    +0.10
    0.4%
    724
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    702
    +0.11
    0.04
    274
    +0.10
    0.04
    724
    +0.09
    0.05
    Negative Logits
    orld
    -0.73
     declared
    -0.64
     conquered
    -0.62
     vandal
    -0.61
     mailed
    -0.58
     recognized
    -0.58
     sought
    -0.58
     thereto
    -0.58
     favourites
    -0.56
     matured
    -0.56
    POSITIVE LOGITS
     GOODMAN
    0.76
     Aires
    0.74
    imaru
    0.72
    ·
    0.71
    hift
    0.71
    ï¸
    0.69
    catentry
    0.65
    problem
    0.65
    ECA
    0.64
     HUGE
    0.63
    Activations Density 0.340%

    No Known Activations