© 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. 37169
    Prev
    Next
    INDEX
    Explanations

    references to organizations and individuals involved in management or leadership roles

    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
    549
    +0.12
    0.6%
    45
    +0.11
    0.5%
    120
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.12
    0.01
    288
    +0.11
    0.01
    639
    +0.10
    0.01
    Negative Logits
    displayText
    -0.93
    æĸ¹
    -0.91
    çīĪ
    -0.78
    Ö¼
    -0.76
    FORE
    -0.74
    ensible
    -0.72
    Sov
    -0.71
    Tube
    -0.69
     {:
    -0.67
    ä
    -0.67
    POSITIVE LOGITS
    alyst
    1.09
    izational
    0.98
    esthetic
    0.95
    istic
    0.93
    thus
    0.87
    xiety
    0.87
    otaur
    0.86
    istical
    0.84
    istics
    0.82
    hedral
    0.81
    Activations Density 0.007%

    No Known Activations