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. 23648
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses 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
    640
    +0.12
    0.6%
    373
    +0.12
    0.5%
    136
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.12
    0.03
    313
    +0.12
    0.03
    648
    +0.10
    0.03
    Negative Logits
     Lans
    -0.69
     Constantine
    -0.67
     bark
    -0.67
     Kro
    -0.66
     Obi
    -0.65
     GSL
    -0.64
     Kurd
    -0.64
     Isa
    -0.63
     McF
    -0.62
     McCartney
    -0.61
    POSITIVE LOGITS
    pmwiki
    1.25
    cgi
    1.24
    forums
    1.24
    wp
    1.17
    forum
    1.16
    sites
    1.13
    uploads
    1.07
    articles
    1.05
    download
    1.05
    pub
    1.05
    Activations Density 0.019%

    No Known Activations