© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 1409
    Prev
    Next
    INDEX
    Explanations

    words related to crime and legal proceedings

    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
    176
    +0.11
    0.5%
    688
    +0.10
    0.5%
    372
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    633
    +0.11
    0.04
    196
    +0.10
    0.03
    555
    +0.10
    0.04
    Negative Logits
    Subject
    -0.63
     NCT
    -0.63
     Digest
    -0.60
    NESS
    -0.59
     Subject
    -0.55
     viol
    -0.55
     Jol
    -0.53
     Group
    -0.53
     Rite
    -0.52
    ioxide
    -0.52
    POSITIVE LOGITS
    been
    1.54
     been
    1.10
     Been
    1.05
    igrated
    1.03
    kered
    0.98
    gotten
    0.97
     gotten
    0.96
    stood
    0.91
    ked
    0.89
    grown
    0.89
    Activations Density 0.189%

    No Known Activations