© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23881
    Prev
    Next
    INDEX
    Explanations

    references to the concept of planning or preparing in advance

    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
    710
    +0.10
    0.5%
    288
    +0.10
    0.4%
    388
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.10
    0.01
    710
    +0.10
    0.01
    388
    +0.09
    0.01
    Negative Logits
     Flavoring
    -0.77
     Klux
    -0.76
    BuyableInstoreAndOnline
    -0.75
    ĪĴ
    -0.72
     Rebell
    -0.71
    sey
    -0.71
    adra
    -0.70
    ById
    -0.67
    DCS
    -0.67
    tons
    -0.65
    POSITIVE LOGITS
     screenings
    0.97
     screening
    0.92
     planning
    0.86
     beforehand
    0.84
    noon
    0.80
     scheduling
    0.80
     staging
    0.79
     informing
    0.77
     schedules
    0.76
     plotting
    0.74
    Activations Density 0.014%

    No Known Activations