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 49152
    5. 8-RES_FS49152-JB
    6. 25586
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 's'

    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
    480
    +0.43
    2.2%
    87
    +0.14
    0.7%
    314
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.43
    0.05
    664
    +0.14
    0.04
    15
    +0.13
    0.05
    Negative Logits
     Niet
    -0.70
     Seym
    -0.61
    Compare
    -0.60
     compar
    -0.59
     Ribbon
    -0.58
     miscar
    -0.57
     Moroc
    -0.56
     RPM
    -0.56
     stacks
    -0.54
     fert
    -0.54
    POSITIVE LOGITS
    leeve
    0.95
    ELF
    0.91
    ources
    0.90
    niper
    0.85
    avior
    0.81
    lightly
    0.79
    ourced
    0.79
    atisf
    0.78
    ustain
    0.77
    wered
    0.76
    Activations Density 0.116%

    No Known Activations