© 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. 7034
    Prev
    Next
    INDEX
    Explanations

    words related to legal processes or bureaucratic procedures

    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
    25
    +0.09
    0.4%
    134
    +0.09
    0.4%
    514
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.09
    0.01
    4
    +0.09
    0.01
    232
    +0.08
    0.01
    Negative Logits
     Jagu
    -0.69
     Hann
    -0.64
    chenko
    -0.63
    borg
    -0.63
    pac
    -0.63
    çĭ
    -0.62
     tremend
    -0.62
    atron
    -0.61
    Italy
    -0.60
    Kick
    -0.60
    POSITIVE LOGITS
    aign
    0.92
    intendent
    0.82
    ople
    0.77
    acters
    0.76
    wealth
    0.74
    imately
    0.72
    ially
    0.68
    ional
    0.68
     NRA
    0.68
    ption
    0.67
    Activations Density 0.028%

    No Known Activations