© 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. 23884
    Prev
    Next
    INDEX
    Explanations

    locations and specific points in time or events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    675
    +0.12
    0.5%
    481
    +0.11
    0.5%
    717
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.03
    257
    +0.11
    0.03
    717
    +0.10
    0.02
    Negative Logits
    rand
    -0.70
    rat
    -0.69
    lain
    -0.67
    criptions
    -0.66
    rss
    -0.65
    above
    -0.65
     caption
    -0.64
    ult
    -0.64
    rating
    -0.63
    gey
    -0.61
    POSITIVE LOGITS
     shores
    1.02
     doorstep
    0.83
    INGTON
    0.82
     Arri
    0.78
     fruition
    0.77
     Medina
    0.75
     Hogwarts
    0.75
     Baghdad
    0.74
     Venice
    0.73
     Calais
    0.73
    Activations Density 0.134%

    No Known Activations