© 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. 836
    Prev
    Next
    INDEX
    Explanations

    phrases or keywords related to the name "Ross"

    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
    682
    +0.12
    0.5%
    25
    +0.11
    0.5%
    466
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    682
    +0.12
    0.02
    466
    +0.11
    0.02
    628
    +0.10
    0.01
    Negative Logits
    rious
    -0.75
    ACTED
    -0.73
    rous
    -0.67
    selves
    -0.65
     à¨
    -0.65
     Countdown
    -0.65
     conspicuous
    -0.62
    lder
    -0.62
    RON
    -0.61
    merce
    -0.61
    POSITIVE LOGITS
    etti
    1.04
    bach
    1.04
    olini
    1.00
    iter
    0.97
    andra
    0.92
    aunders
    0.89
    andowski
    0.85
    inian
    0.84
    dale
    0.84
    endale
    0.82
    Activations Density 0.059%

    No Known Activations