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. 23910
    Prev
    Next
    INDEX
    Explanations

    narratives involving toys and play experiences

    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
    640
    +0.28
    1.4%
    481
    +0.14
    0.7%
    442
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.14
    107
    +0.14
    0.13
    442
    +0.14
    0.13
    Negative Logits
    xual
    -0.91
     ability
    -0.80
     eleph
    -0.71
     prosec
    -0.71
     coral
    -0.70
     regenerate
    -0.69
    yip
    -0.68
     capability
    -0.68
     dynam
    -0.67
     frontline
    -0.67
    POSITIVE LOGITS
    Then
    1.74
    Advertisement
    1.70
    Eventually
    1.68
    SPONSORED
    1.60
    Instead
    1.58
    Within
    1.54
    Shortly
    1.52
    Soon
    1.52
    Later
    1.52
    Fortunately
    1.52
    Activations Density 0.408%

    No Known Activations