© 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. 41719
    Prev
    Next
    INDEX
    Explanations

    variations of the letter 'P' in sequences

    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
    659
    +0.17
    0.8%
    578
    +0.13
    0.6%
    482
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.17
    0.06
    482
    +0.13
    0.05
    578
    +0.12
    0.04
    Negative Logits
     Rebels
    -0.86
     diplom
    -0.76
     GOODMAN
    -0.68
     Breaking
    -0.66
     adm
    -0.63
    ģĸ
    -0.62
     EntityItem
    -0.62
     Orche
    -0.61
     ancest
    -0.61
     juggling
    -0.61
    POSITIVE LOGITS
    aired
    1.27
    ardon
    1.26
    ivot
    1.25
    ierce
    1.21
    erenn
    1.20
    ainted
    1.19
    ussy
    1.19
    oultry
    1.17
    airs
    1.16
    ushing
    1.14
    Activations Density 0.032%

    No Known Activations