© 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 49152
    9. 8-RES_FS49152-JB
    11. 37465
    Prev
    Next
    INDEX
    Explanations

    references to states in a legislative or regulatory context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    718
    +0.13
    0.6%
    357
    +0.11
    0.5%
    601
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.13
    0.03
    718
    +0.11
    0.03
    357
    +0.10
    0.03
    Negative Logits
     Insp
    -0.68
     Notting
    -0.68
     Pastebin
    -0.66
     Lect
    -0.65
     Spit
    -0.64
     RTX
    -0.64
     Brilliant
    -0.63
    sett
    -0.62
     Nose
    -0.62
    rious
    -0.61
    POSITIVE LOGITS
    manship
    1.34
    men
    1.11
     legislatures
    1.00
    ide
    0.94
    man
    0.93
    wide
    0.87
    rooms
    0.86
     legalizing
    0.83
     bordering
    0.82
    boro
    0.81
    Activations Density 0.028%

    No Known Activations