© 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 12288
    9. 8-RES_FS12288-JB
    11. 1222
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    19
    +0.13
    0.6%
    216
    +0.13
    0.6%
    128
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.13
    0.03
    19
    +0.13
    0.03
    22
    +0.13
    0.03
    Negative Logits
    hound
    -0.77
    staking
    -0.70
     thumbs
    -0.69
    æ©Ł
    -0.65
     deaf
    -0.64
    perty
    -0.64
     bait
    -0.62
     carriers
    -0.61
     competent
    -0.60
    giene
    -0.59
    POSITIVE LOGITS
    rict
    1.16
    upid
    1.13
    oppable
    1.11
    retch
    1.11
    alker
    1.10
    oppers
    1.08
    itute
    1.08
    rikes
    1.07
    REAM
    1.06
    amped
    1.06
    Activations Density 0.057%

    No Known Activations