Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 12362
    Prev
    Next
    INDEX
    Explanations

    adjectives emphasizing the intensity or quality of something in a positive or negative manner

    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
    83
    +0.10
    0.4%
    393
    +0.10
    0.4%
    206
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.10
    0.01
    130
    +0.10
    0.01
    83
    +0.09
    0.01
    Negative Logits
    iture
    -0.74
    itures
    -0.73
    acas
    -0.71
     Incident
    -0.66
    alyst
    -0.66
    iage
    -0.65
    achus
    -0.65
    577
    -0.62
    enment
    -0.61
    idas
    -0.60
    POSITIVE LOGITS
     WIN
    0.70
    mean
    0.68
     fucked
    0.66
    ittle
    0.64
     istg
    0.61
     mean
    0.60
    idine
    0.60
     ner
    0.60
     correctness
    0.58
    repeat
    0.58
    Activations Density 0.051%

    No Known Activations