© 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. 19822
    Prev
    Next
    INDEX
    Explanations

    instances of the word "every"

    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
    496
    +0.12
    0.6%
    230
    +0.11
    0.5%
    616
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.12
    0.04
    163
    +0.11
    0.03
    237
    +0.09
    0.03
    Negative Logits
    olas
    -0.78
    phabet
    -0.75
    dict
    -0.65
     Presence
    -0.64
    isson
    -0.63
     Graves
    -0.61
     Osw
    -0.61
    ees
    -0.60
     Pru
    -0.58
     Papers
    -0.58
    POSITIVE LOGITS
    THING
    1.56
     conceivable
    1.49
     imaginable
    1.40
    where
    1.11
     single
    1.06
     inch
    1.06
    thin
    1.01
     aspect
    1.01
     ounce
    1.01
    single
    0.97
    Activations Density 0.045%

    No Known Activations