© 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 24576
    9. 8-RES_FS24576-JB
    11. 7184
    Prev
    Next
    INDEX
    Explanations

    numeric data, particularly related to statistics and records

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    373
    +0.13
    0.6%
    605
    +0.10
    0.5%
    25
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.13
    0.03
    547
    +0.10
    0.03
    25
    +0.10
    0.03
    Negative Logits
     knots
    -0.66
    eric
    -0.63
    eln
    -0.62
     meanwhile
    -0.60
    bp
    -0.60
    facing
    -0.59
     grateful
    -0.59
    atio
    -0.58
    respond
    -0.55
    hend
    -0.54
    POSITIVE LOGITS
     inception
    0.89
     Era
    0.69
     era
    0.63
     landfall
    0.62
     debuted
    0.61
     Trafford
    0.60
    eties
    0.60
     captivity
    0.60
     infancy
    0.59
    roots
    0.59
    Activations Density 0.244%

    No Known Activations