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 3072
    5. 8-RES_FS3072-JB
    6. 1070
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and player transfer activities

    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
    434
    +0.10
    0.5%
    182
    +0.10
    0.4%
    500
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    434
    +0.10
    0.08
    286
    +0.10
    0.09
    10
    +0.10
    0.07
    Negative Logits
    ecd
    -0.76
     stereotype
    -0.75
    ĸļ
    -0.74
    often
    -0.72
     contrasted
    -0.71
     defeats
    -0.70
    giene
    -0.70
     Errors
    -0.68
    overty
    -0.68
     poorest
    -0.68
    POSITIVE LOGITS
     plans
    1.21
     rumored
    1.02
     upcoming
    0.98
     forthcoming
    0.97
     TBA
    0.96
     imminent
    0.93
     impending
    0.87
     negotiations
    0.87
     intends
    0.87
    soon
    0.87
    Activations Density 3.369%

    No Known Activations