© 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. 10145
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense

    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
    102
    +0.21
    1.0%
    55
    +0.13
    0.6%
    208
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.21
    0.16
    55
    +0.13
    0.15
    566
    +0.13
    0.11
    Negative Logits
    inav
    -0.88
     hypotheses
    -0.72
     VIDEOS
    -0.72
     Formation
    -0.71
     Extend
    -0.70
     loops
    -0.69
    artments
    -0.69
    eways
    -0.68
     Horses
    -0.68
     spans
    -0.68
    POSITIVE LOGITS
     able
    1.18
     unemploy
    1.07
     assassinated
    1.03
     willing
    1.02
     born
    1.01
     diagnosed
    1.00
     married
    0.99
     ineligible
    0.98
     unable
    0.97
     fluent
    0.95
    Activations Density 0.610%

    No Known Activations