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. 384
    Prev
    Next
    INDEX
    Explanations

    Russian language characters and words

    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
    103
    +0.13
    0.6%
    107
    +0.13
    0.6%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.13
    0.06
    103
    +0.13
    0.06
    48
    +0.10
    0.05
    Negative Logits
     Franch
    -0.71
    theless
    -0.67
    essa
    -0.67
    ulators
    -0.66
     concede
    -0.65
     gad
    -0.63
     board
    -0.62
     Ada
    -0.61
     Bun
    -0.61
     venture
    -0.61
    POSITIVE LOGITS
    Į
    1.99
    ¢
    1.90
    ¹
    1.89
    ¥
    1.87
    ²
    1.86
    ±
    1.85
    ´
    1.85
    Ń
    1.84
    Ķ
    1.80
    ³
    1.80
    Activations Density 0.252%

    No Known Activations