© 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 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. 42923
    Prev
    Next
    INDEX
    Explanations

    words related to the indefinite article "a" and its variants

    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
    36
    +0.20
    1.0%
    393
    +0.13
    0.6%
    640
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.20
    0.06
    270
    +0.13
    0.02
    343
    +0.12
    0.02
    Negative Logits
    worthiness
    -0.88
    ablishment
    -0.79
    buquerque
    -0.72
    important
    -0.67
    Init
    -0.66
    Requ
    -0.66
    agree
    -0.65
    Things
    -0.65
    bernatorial
    -0.65
    issues
    -0.64
    POSITIVE LOGITS
     combination
    1.13
     pseudonym
    1.12
     technique
    0.99
     borrowed
    0.96
     specially
    0.91
     sophisticated
    0.89
     mixture
    0.86
     computer
    0.84
     tripod
    0.84
     lot
    0.84
    Activations Density 0.071%

    No Known Activations