© 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. 1340
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, products, publications, and 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
    481
    +0.15
    0.7%
    447
    +0.13
    0.6%
    420
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.08
    326
    +0.13
    0.07
    420
    +0.11
    0.05
    Negative Logits
    ],"
    -0.87
    âĹ¼
    -0.70
    umbn
    -0.67
    interstitial
    -0.65
    docker
    -0.64
    uminati
    -0.63
    ocobo
    -0.63
    strument
    -0.62
    chest
    -0.61
     Guant
    -0.61
    POSITIVE LOGITS
    ONSORED
    0.79
     agrees
    0.79
    ogether
    0.79
     assures
    0.76
     also
    0.74
     disagrees
    0.72
    ensibly
    0.71
     retains
    0.71
     however
    0.70
    eday
    0.69
    Activations Density 0.577%

    No Known Activations