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 6144
    5. 8-RES_FS6144-JB
    6. 5457
    Prev
    Next
    INDEX
    Explanations

    passages related to American football positions and scenarios

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    314
    +0.15
    0.7%
    373
    +0.11
    0.5%
    722
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.12
    608
    +0.11
    0.12
    257
    +0.11
    0.07
    Negative Logits
    Film
    -0.69
     Awakens
    -0.64
    resy
    -0.63
    beat
    -0.62
    film
    -0.62
    glass
    -0.59
     Offline
    -0.58
    orge
    -0.57
    enda
    -0.57
    atre
    -0.55
    POSITIVE LOGITS
     whichever
    0.83
     varying
    0.75
     whence
    0.72
    Magikarp
    0.71
    tnc
    0.70
     regards
    0.69
     determining
    0.68
     hopes
    0.66
    respective
    0.65
     which
    0.64
    Activations Density 1.812%

    No Known Activations