© 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. 1239
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and events in a news context

    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
    608
    +0.13
    0.6%
    393
    +0.13
    0.6%
    362
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    601
    +0.13
    0.03
    393
    +0.13
    0.04
    608
    +0.11
    0.04
    Negative Logits
    Discuss
    -0.77
    ftime
    -0.75
    ï¸
    -0.72
    elle
    -0.71
    vier
    -0.70
     Citation
    -0.70
    ccording
    -0.69
    wow
    -0.69
    quest
    -0.69
    sure
    -0.68
    POSITIVE LOGITS
     its
    0.75
     vanquished
    0.69
     ours
    0.66
     slavery
    0.66
     theirs
    0.65
     Silicon
    0.64
     destiny
    0.63
     Olympia
    0.63
     Chinatown
    0.61
     neighbouring
    0.61
    Activations Density 0.180%

    No Known Activations