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 24576
    5. 8-RES_FS24576-JB
    6. 8331
    Prev
    Next
    INDEX
    Explanations

    words related to hindlimbs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    23
    +0.16
    0.7%
    641
    +0.10
    0.4%
    459
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.16
    0.01
    288
    +0.10
    0.01
    240
    +0.09
    0.01
    Negative Logits
    hips
    -0.76
    oice
    -0.68
    ãĥ¯
    -0.68
     Clause
    -0.68
    loo
    -0.66
    iott
    -0.66
    aukee
    -0.64
     Sunshine
    -0.63
    inic
    -0.63
    ç¥ŀ
    -0.61
    POSITIVE LOGITS
    sight
    1.17
    ering
    0.84
    nesses
    0.84
    quarters
    0.83
    ned
    0.80
    secondary
    0.77
    sters
    0.76
    vid
    0.74
    rance
    0.74
    ¿½
    0.72
    Activations Density 0.028%

    No Known Activations