© 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. 10355
    Prev
    Next
    INDEX
    Explanations

    technical details and features mentioned in product reviews

    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
    373
    +0.17
    0.8%
    277
    +0.12
    0.5%
    237
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.17
    0.05
    237
    +0.12
    0.04
    288
    +0.12
    0.08
    Negative Logits
    needed
    -0.67
    inctions
    -0.67
    Adapt
    -0.60
    urally
    -0.60
    blem
    -0.59
     challeng
    -0.59
    rosso
    -0.59
    acerb
    -0.59
    struction
    -0.58
    iquette
    -0.57
    POSITIVE LOGITS
     standpoint
    1.49
     onwards
    1.33
     vantage
    1.11
     perspective
    1.08
     onward
    1.05
     sources
    0.97
     outset
    0.82
    ratch
    0.81
     backgrounds
    0.77
     Shutterstock
    0.73
    Activations Density 0.834%

    No Known Activations