© 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. 37262
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating actions affecting various situations or individuals

    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
    301
    +0.12
    0.5%
    488
    +0.11
    0.5%
    277
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    541
    +0.12
    0.05
    488
    +0.11
    0.05
    390
    +0.11
    0.04
    Negative Logits
    urai
    -0.62
    enos
    -0.57
     CoC
    -0.56
     Cliff
    -0.56
     nature
    -0.55
     DRAGON
    -0.55
    Poké
    -0.53
     Bees
    -0.53
     Eth
    -0.53
     WH
    -0.53
    POSITIVE LOGITS
     by
    1.15
     aback
    0.93
    bys
    0.84
    by
    0.84
     BY
    0.84
    ĸļ
    0.83
    By
    0.75
     By
    0.72
    linger
    0.72
    pez
    0.71
    Activations Density 0.278%

    No Known Activations