© 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. 9875
    Prev
    Next
    INDEX
    Explanations

    the name "Chuck"

    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
    440
    +0.12
    0.5%
    54
    +0.09
    0.4%
    330
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.02
    440
    +0.09
    0.02
    81
    +0.09
    0.02
    Negative Logits
    worldly
    -0.82
    ĺħ
    -0.81
    omorphic
    -0.72
     anten
    -0.69
    xual
    -0.68
    ocard
    -0.66
    haps
    -0.66
     pregn
    -0.66
     glands
    -0.65
    senal
    -0.64
    POSITIVE LOGITS
     Schumer
    1.04
    anut
    1.02
     Grassley
    1.01
    wagon
    0.99
     Norris
    0.96
    ronics
    0.90
    bowl
    0.89
    tail
    0.88
    meat
    0.85
     Wend
    0.80
    Activations Density 0.050%

    No Known Activations