© 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. 1573
    Prev
    Next
    INDEX
    Explanations

    descriptions of vehicles with their license plate numbers

    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
    479
    +0.15
    0.7%
    496
    +0.14
    0.7%
    497
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.15
    0.06
    479
    +0.14
    0.04
    176
    +0.13
    0.04
    Negative Logits
     gobl
    -0.94
    bryce
    -0.88
    ouston
    -0.85
    gob
    -0.78
    phis
    -0.78
    iverpool
    -0.77
    ryce
    -0.77
     dwarves
    -0.77
    mel
    -0.76
    uj
    -0.76
    POSITIVE LOGITS
     Single
    1.30
     Miscellaneous
    1.29
     Repeat
    1.29
     Relationship
    1.26
     Casual
    1.25
     Physical
    1.24
     Practice
    1.23
     Delivery
    1.23
     Distribution
    1.22
     Poster
    1.21
    Activations Density 0.324%

    No Known Activations