© 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 49152
    9. 8-RES_FS49152-JB
    11. 26596
    Prev
    Next
    INDEX
    Explanations

    identifiers or names related to specific people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    679
    +0.13
    0.6%
    526
    +0.10
    0.5%
    605
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.01
    659
    +0.10
    0.01
    288
    +0.09
    0.01
    Negative Logits
    forms
    -0.79
    lees
    -0.75
    conservancy
    -0.72
    utical
    -0.70
    wagen
    -0.69
    ISTER
    -0.69
    uting
    -0.68
    taboola
    -0.68
    uters
    -0.68
    igion
    -0.66
    POSITIVE LOGITS
    rax
    0.87
    rous
    0.87
    urous
    0.76
    rav
    0.76
    hedon
    0.75
    edo
    0.74
     Shack
    0.72
    hered
    0.71
    obin
    0.71
    fall
    0.71
    Activations Density 0.008%

    No Known Activations