© 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. 1636
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action and supporting a cause

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    710
    +0.12
    0.5%
    314
    +0.12
    0.5%
    477
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.12
    0.02
    521
    +0.12
    0.02
    666
    +0.12
    0.02
    Negative Logits
     ILCS
    -0.90
     largeDownload
    -0.75
    artisan
    -0.71
     Fem
    -0.71
    gom
    -0.70
    ividually
    -0.66
    Advertisements
    -0.66
    fman
    -0.66
    akov
    -0.65
    )))
    -0.65
    POSITIVE LOGITS
    aping
    0.65
    ENA
    0.62
     commuting
    0.61
     Cancel
    0.59
     retake
    0.59
    Learn
    0.59
     thanking
    0.58
     commute
    0.58
    no
    0.58
    email
    0.58
    Activations Density 0.042%

    No Known Activations