© 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. 9290
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms or concepts related to research and engineering

    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
    384
    +0.12
    0.5%
    393
    +0.11
    0.5%
    527
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.12
    0.06
    393
    +0.11
    0.06
    120
    +0.09
    0.05
    Negative Logits
    ĸļ
    -0.91
    west
    -0.78
    stown
    -0.77
    wolf
    -0.71
    KEN
    -0.71
    West
    -0.67
     Geral
    -0.65
     Ruth
    -0.64
    nee
    -0.64
     Kath
    -0.63
    POSITIVE LOGITS
     accessories
    1.23
     equipment
    1.16
     gadgets
    1.12
     appliances
    1.12
     tools
    1.10
     technologies
    1.09
     mater
    1.05
     artifacts
    1.00
     weaponry
    0.98
     components
    0.98
    Activations Density 0.290%

    No Known Activations