© 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. 12012
    Prev
    Next
    INDEX
    Explanations

    terms related to physical body parts

    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
    709
    +0.11
    0.5%
    616
    +0.11
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    588
    +0.11
    0.01
    396
    +0.11
    0.01
    557
    +0.10
    0.01
    Negative Logits
     mask
    -0.62
    ween
    -0.59
     Niet
    -0.59
    flush
    -0.59
     masks
    -0.59
     elig
    -0.58
     Homo
    -0.58
     fer
    -0.57
     awake
    -0.57
     Woodward
    -0.56
    POSITIVE LOGITS
    ageddon
    1.43
    aceutical
    1.37
    ovie
    1.11
    ament
    1.04
    ichael
    1.03
    essage
    1.02
    ony
    1.02
    achine
    0.98
    strong
    0.92
    onica
    0.92
    Activations Density 0.014%

    No Known Activations