© 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. 42922
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "the" in different contexts

    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
    393
    +0.17
    0.8%
    362
    +0.14
    0.6%
    649
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.17
    0.04
    385
    +0.14
    0.03
    393
    +0.11
    0.03
    Negative Logits
    tle
    -0.74
    CVE
    -0.69
    thood
    -0.68
    Percent
    -0.68
     namely
    -0.67
     suppose
    -0.66
    oka
    -0.65
    URE
    -0.65
    ION
    -0.64
    UI
    -0.63
    POSITIVE LOGITS
     entirety
    1.20
     midst
    1.13
     halls
    1.09
     veins
    1.06
     corridors
    1.03
     ranks
    1.02
     confines
    1.02
     remainder
    1.02
     woods
    1.01
     motions
    1.01
    Activations Density 0.049%

    No Known Activations