© 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. 1238
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant changes or actions being taken

    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
    749
    +0.12
    0.6%
    224
    +0.12
    0.5%
    575
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.12
    0.03
    749
    +0.12
    0.03
    540
    +0.12
    0.03
    Negative Logits
     sqor
    -0.80
    vae
    -0.72
    omial
    -0.72
    aez
    -0.64
    ordon
    -0.63
     attm
    -0.63
    Condition
    -0.62
    errors
    -0.62
    nat
    -0.61
    english
    -0.61
    POSITIVE LOGITS
    backs
    0.95
    able
    0.94
     toward
    0.93
    ments
    0.93
     towards
    0.92
    ment
    0.80
    over
    0.78
    rers
    0.78
     forward
    0.74
    ler
    0.73
    Activations Density 0.049%

    No Known Activations