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 49152
    5. 8-RES_FS49152-JB
    6. 37122
    Prev
    Next
    INDEX
    Explanations

    instances of kissing and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    526
    +0.13
    0.6%
    326
    +0.11
    0.5%
    1
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.01
    599
    +0.11
    0.01
    526
    +0.10
    0.00
    Negative Logits
    é¾
    -1.06
    quickShipAvailable
    -0.79
     Flavoring
    -0.75
     Forbes
    -0.73
    ifted
    -0.69
    IJ
    -0.68
    æ©Ł
    -0.66
    izoph
    -0.66
    äºĶ
    -0.65
    ancial
    -0.64
    POSITIVE LOGITS
     goodbye
    1.29
    kiss
    1.16
     kiss
    1.12
     Kiss
    1.04
     kisses
    1.02
     kissing
    0.97
     passionately
    0.97
     kissed
    0.96
    creen
    0.93
     Goodbye
    0.92
    Activations Density 0.009%

    No Known Activations