© 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. 41527
    Prev
    Next
    INDEX
    Explanations

    references to the pronoun "them."

    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
    553
    +0.11
    0.5%
    61
    +0.10
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.11
    0.02
    689
    +0.10
    0.02
    61
    +0.10
    0.02
    Negative Logits
     RTX
    -0.80
    mire
    -0.75
    Limit
    -0.65
    Charg
    -0.64
     Farn
    -0.63
    Press
    -0.63
    083
    -0.61
    Pause
    -0.60
    politics
    -0.60
     Fulton
    -0.60
    POSITIVE LOGITS
    atic
    1.10
    atically
    1.01
    selves
    0.91
     perished
    0.84
     selves
    0.84
     were
    0.82
    alian
    0.81
     individually
    0.80
     are
    0.80
     originated
    0.79
    Activations Density 0.023%

    No Known Activations