© 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. 646
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and entertainment, specifically referring to blockchain, film productions, and indie films

    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
    372
    +0.10
    0.4%
    582
    +0.09
    0.4%
    429
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    582
    +0.10
    0.04
    740
    +0.09
    0.06
    429
    +0.09
    0.05
    Negative Logits
    TPPStreamerBot
    -0.95
    Draft
    -0.83
    ))))
    -0.76
    ashington
    -0.75
    cussion
    -0.74
    Newsletter
    -0.73
    )))
    -0.73
    External
    -0.71
    inventoryQuantity
    -0.71
    statement
    -0.70
    POSITIVE LOGITS
     protagonist
    1.28
     narrator
    1.12
     discovers
    1.12
     heroine
    1.10
     flashbacks
    1.06
     detective
    1.00
     kidnapped
    0.99
     protagonists
    0.98
     adventures
    0.96
     learns
    0.95
    Activations Density 1.426%

    No Known Activations