© 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. 10067
    Prev
    Next
    INDEX
    Explanations

    words related to legal or regulatory actions

    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
    373
    +0.24
    1.2%
    671
    +0.10
    0.5%
    202
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    571
    +0.24
    0.04
    422
    +0.10
    0.04
    607
    +0.10
    0.04
    Negative Logits
    milo
    -0.66
    iolet
    -0.59
    terday
    -0.55
    Cola
    -0.53
    oslov
    -0.52
     Parenthood
    -0.51
     Topic
    -0.50
    myra
    -0.50
     Aires
    -0.49
     Matters
    -0.49
    POSITIVE LOGITS
    iest
    0.98
    liest
    0.89
    forts
    0.71
    same
    0.70
    adle
    0.68
    osphere
    0.67
    formation
    0.65
    hest
    0.64
    waters
    0.62
    ultimate
    0.59
    Activations Density 0.265%

    No Known Activations