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 768
    5. 8-RES_FS768-JB
    6. 498
    Prev
    Next
    INDEX
    Explanations

    terms related to sports, competitions, and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    651
    +0.12
    0.6%
    447
    +0.12
    0.6%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.24
    651
    +0.12
    0.21
    531
    +0.12
    0.14
    Negative Logits
    anguages
    -0.73
    cro
    -0.69
    iri
    -0.69
    atem
    -0.65
    pie
    -0.64
    poor
    -0.63
    inks
    -0.62
     Species
    -0.62
    ailable
    -0.61
    organic
    -0.61
    POSITIVE LOGITS
     finale
    1.02
     anniversary
    1.01
     debacle
    0.96
     season
    0.96
     festivities
    0.94
    iversary
    0.90
     unfold
    0.89
     involving
    0.88
     organisers
    0.88
     postponed
    0.87
    Activations Density 5.561%

    No Known Activations