© 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. 18909
    Prev
    Next
    INDEX
    Explanations

    age information mentioned in the text

    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
    220
    +0.11
    0.5%
    459
    +0.11
    0.5%
    430
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.11
    0.04
    310
    +0.11
    0.04
    198
    +0.09
    0.03
    Negative Logits
     constitu
    -0.68
    ebin
    -0.63
    access
    -0.60
    izens
    -0.60
     dictators
    -0.60
     stabilization
    -0.57
    oids
    -0.57
     âī
    -0.57
     manifold
    -0.57
     elimination
    -0.57
    POSITIVE LOGITS
    %,
    0.88
     Rue
    0.83
    %-
    0.79
    yo
    0.78
    rd
    0.74
    th
    0.73
    %;
    0.72
     Downing
    0.71
    cm
    0.71
    ½
    0.70
    Activations Density 0.052%

    No Known Activations