© 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. 10307
    Prev
    Next
    INDEX
    Explanations

    the word "little"

    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
    455
    +0.12
    0.5%
    408
    +0.10
    0.5%
    344
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.12
    0.04
    455
    +0.10
    0.04
    344
    +0.10
    0.04
    Negative Logits
    ser
    -0.76
    ses
    -0.70
    llers
    -0.69
    agents
    -0.68
    midt
    -0.65
    wered
    -0.64
    draft
    -0.64
    ades
    -0.64
    creator
    -0.62
    dor
    -0.62
    POSITIVE LOGITS
     else
    0.97
     resemblance
    0.89
     sympathy
    0.88
     inclination
    0.87
     fuss
    0.85
     patience
    0.83
     recourse
    0.83
     regard
    0.83
     doubt
    0.82
     indication
    0.82
    Activations Density 0.095%

    No Known Activations