© 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. 9651
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to medications

    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
    92
    +0.10
    0.4%
    339
    +0.09
    0.4%
    601
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.10
    0.06
    738
    +0.09
    0.05
    678
    +0.09
    0.05
    Negative Logits
     careers
    -0.75
    entry
    -0.74
    FontSize
    -0.73
    issance
    -0.71
     Inquiry
    -0.70
    ateurs
    -0.70
    rentices
    -0.69
    ittees
    -0.69
     Generations
    -0.69
    projects
    -0.68
    POSITIVE LOGITS
     salts
    1.39
     sodium
    1.38
     potassium
    1.35
     ammonia
    1.34
    anol
    1.33
     Sodium
    1.32
     ethanol
    1.29
     sulph
    1.27
    aldehyde
    1.27
     iodine
    1.27
    Activations Density 0.751%

    No Known Activations