© 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 49152
    5. 8-RES_FS49152-JB
    6. 26587
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities, particularly "Springs" and "Spa."

    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
    575
    +0.12
    0.6%
    685
    +0.12
    0.5%
    99
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.01
    288
    +0.12
    0.02
    99
    +0.11
    0.01
    Negative Logits
    phas
    -0.78
    ctica
    -0.75
    ograp
    -0.72
    oses
    -0.70
    haul
    -0.69
    İĭ
    -0.68
    ĪĴ
    -0.67
    phant
    -0.67
    joice
    -0.67
    ographers
    -0.67
    POSITIVE LOGITS
    atoon
    0.89
    sburgh
    0.77
    ONSORED
    0.75
    heet
    0.73
    atial
    0.72
    ORTS
    0.71
    KI
    0.70
     Springs
    0.70
    atchewan
    0.70
    EED
    0.69
    Activations Density 0.024%

    No Known Activations