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. 26444
    Prev
    Next
    INDEX
    Explanations

    instances of object creation in programming contexts

    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
    373
    +0.14
    0.7%
    588
    +0.11
    0.5%
    339
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.14
    0.01
    499
    +0.11
    0.01
    588
    +0.11
    0.01
    Negative Logits
    SPONSORED
    -0.90
    itta
    -0.84
    ppe
    -0.79
    ocene
    -0.78
    76561
    -0.75
    yip
    -0.74
    orsi
    -0.72
    ¨
    -0.70
    iage
    -0.69
    chnology
    -0.68
    POSITIVE LOGITS
     Array
    0.87
    Instance
    0.82
    bies
    0.81
    bie
    0.80
     YORK
    0.80
     York
    0.76
     Hash
    0.74
     byte
    0.71
     google
    0.70
     Vector
    0.69
    Activations Density 0.008%

    No Known Activations