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. 1634
    Prev
    Next
    INDEX
    Explanations

    information related to political figures, government actions, and policies

    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
    365
    +0.12
    0.5%
    463
    +0.12
    0.5%
    620
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.12
    620
    +0.12
    0.04
    344
    +0.12
    0.11
    Negative Logits
    ãĤ´
    -0.69
     ¯
    -0.65
    aurus
    -0.65
    =/
    -0.64
    forcer
    -0.61
    Ö¼
    -0.60
    aco
    -0.60
    ðŁĺ
    -0.60
    affer
    -0.60
    ouf
    -0.60
    POSITIVE LOGITS
     respective
    1.12
     themselves
    1.10
     respectively
    1.05
     careers
    0.94
     varying
    0.94
     theirs
    0.85
     histories
    0.85
     individually
    0.84
     apiece
    0.84
     overlapping
    0.83
    Activations Density 3.097%

    No Known Activations