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. 23758
    Prev
    Next
    INDEX
    Explanations

    articles and pronouns in the text

    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
    609
    +0.10
    0.5%
    214
    +0.09
    0.4%
    372
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    694
    +0.10
    0.02
    314
    +0.09
    0.00
    18
    +0.09
    0.03
    Negative Logits
     Accountability
    -0.72
     Provision
    -0.72
     Exper
    -0.69
     meanwhile
    -0.67
     Finance
    -0.62
     Fighters
    -0.59
     Akin
    -0.59
     Nadu
    -0.58
     Voy
    -0.58
     Price
    -0.57
    POSITIVE LOGITS
    aps
    1.09
    ocl
    1.09
    ctic
    0.98
    alian
    0.97
    ocratic
    0.95
    otypes
    0.94
    pron
    0.94
    aping
    0.94
    odic
    0.93
    eper
    0.91
    Activations Density 0.147%

    No Known Activations