© 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. 9768
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters and law enforcement

    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
    481
    +0.24
    1.1%
    429
    +0.13
    0.6%
    384
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.24
    0.05
    429
    +0.13
    0.05
    393
    +0.10
    0.08
    Negative Logits
    \-
    -0.72
    ovember
    -0.71
    Finish
    -0.70
    inez
    -0.69
    alert
    -0.66
     Correction
    -0.66
     RELEASE
    -0.65
    Alert
    -0.65
    akra
    -0.65
    Correction
    -0.65
    POSITIVE LOGITS
     ones
    1.25
    those
    1.00
     hybrids
    0.97
     those
    0.96
     newcomers
    0.88
     lone
    0.87
     newer
    0.85
     homegrown
    0.85
     lesser
    0.84
     hordes
    0.84
    Activations Density 0.782%

    No Known Activations