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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4775
    Prev
    Next
    INDEX
    Explanations

    medical procedures and actions related to 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_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
    175
    +0.12
    0.5%
    756
    +0.10
    0.5%
    389
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.12
    0.06
    575
    +0.10
    0.07
    401
    +0.10
    0.06
    Negative Logits
    laughs
    -0.69
    ADS
    -0.63
     Sins
    -0.62
     Mouth
    -0.59
    OV
    -0.57
    ESCO
    -0.55
    stown
    -0.55
     Invention
    -0.54
    Lot
    -0.54
    pub
    -0.54
    POSITIVE LOGITS
     are
    1.33
     were
    1.31
     weren
    1.21
     aren
    1.20
     expire
    1.12
     exist
    1.09
     appear
    1.07
     resonate
    1.05
     differ
    1.03
     coincide
    1.03
    Activations Density 0.358%

    No Known Activations