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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 2125
    Prev
    Next
    INDEX
    Explanations

    information related to sports matches 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_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    657
    +0.10
    0.5%
    651
    +0.10
    0.4%
    198
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.10
    0.10
    657
    +0.10
    0.07
    540
    +0.09
    0.08
    Negative Logits
    sonian
    -0.82
    achev
    -0.74
    aft
    -0.74
    xon
    -0.66
    reprene
    -0.64
    azon
    -0.63
    obook
    -0.63
    bara
    -0.63
    ogle
    -0.63
    onomic
    -0.63
    POSITIVE LOGITS
     opener
    1.08
     unbeaten
    0.90
     against
    0.89
    Tonight
    0.87
     finale
    0.81
     played
    0.80
     tonight
    0.80
    day
    0.79
     Recap
    0.78
     Played
    0.77
    Activations Density 0.728%

    No Known Activations