© 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 3072
    9. 8-RES_FS3072-JB
    11. 3032
    Prev
    Next
    INDEX
    Explanations

    technology-related terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    452
    +0.13
    0.6%
    71
    +0.10
    0.4%
    542
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.13
    608
    +0.10
    0.11
    452
    +0.09
    0.06
    Negative Logits
    abouts
    -0.77
    uana
    -0.76
    pload
    -0.72
     compensated
    -0.70
    istan
    -0.70
    arettes
    -0.66
    enged
    -0.66
    houses
    -0.66
     accompanied
    -0.65
    bang
    -0.65
    POSITIVE LOGITS
     tenets
    1.22
     principles
    1.18
     tradition
    1.18
     sentiments
    1.16
     principle
    1.15
     premise
    1.10
     notion
    1.09
     ideals
    1.09
     traditions
    1.08
     ethos
    1.04
    Activations Density 2.131%

    No Known Activations