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 768
    5. 8-RES_FS768-JB
    6. 159
    Prev
    Next
    INDEX
    Explanations

    information related to news articles and current 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
    493
    +0.10
    0.5%
    181
    +0.10
    0.4%
    731
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.10
    0.10
    706
    +0.10
    0.09
    493
    +0.09
    0.07
    Negative Logits
    ÙĴ
    -0.86
    mittedly
    -0.84
    âĹ¼
    -0.80
    theless
    -0.77
    TEXTURE
    -0.77
    DATA
    -0.77
    ODUCT
    -0.72
    inarily
    -0.72
    Footnote
    -0.71
    iably
    -0.71
    POSITIVE LOGITS
     Replay
    1.18
     Kavanaugh
    1.01
     Dems
    0.95
     Says
    0.95
     slams
    0.90
    ?]
    0.89
    ?'
    0.88
     Latest
    0.84
     Shutterstock
    0.83
    !'
    0.82
    Activations Density 5.692%

    No Known Activations