Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 761
    Prev
    Next
    INDEX
    Explanations

    descriptions of a person's physical appearance

    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
    312
    +0.12
    0.6%
    762
    +0.10
    0.5%
    14
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.05
    312
    +0.10
    0.04
    762
    +0.10
    0.05
    Negative Logits
     DRM
    -0.80
    xit
    -0.76
    ezvous
    -0.76
     closure
    -0.73
     Destination
    -0.72
     mediation
    -0.72
    ctuary
    -0.71
     SOS
    -0.71
     contingency
    -0.70
     Ending
    -0.70
    POSITIVE LOGITS
     stature
    1.47
     taller
    1.38
     athlet
    1.30
     skinny
    1.29
     slender
    1.25
     physique
    1.24
     waist
    1.23
     tallest
    1.20
     tall
    1.14
     curv
    1.12
    Activations Density 0.504%

    No Known Activations