Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23090
    Prev
    Next
    INDEX
    Explanations

    discussions and mentions of contracts and agreements

    oai_token-act-pair · gpt-4o-miniTriggered 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
    87
    +0.34
    2.0%
    756
    +0.32
    1.9%
    481
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.34
    -0.02
    756
    +0.32
    -0.01
    64
    +0.15
    -0.08
    Negative Logits
     mug
    -0.57
    natureconservancy
    -0.55
     pee
    -0.55
     moms
    -0.55
     Freak
    -0.53
     bite
    -0.52
     scams
    -0.52
     goofy
    -0.52
     racket
    -0.51
     hurting
    -0.51
    POSITIVE LOGITS
    sequently
    0.92
    Therefore
    0.81
    Furthermore
    0.79
     furthermore
    0.78
    Additionally
    0.76
    Thus
    0.72
    theless
    0.71
     Lastly
    0.70
    thus
    0.70
    Secondly
    0.69
    Activations Density 1.423%

    No Known Activations