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. 23213
    Prev
    Next
    INDEX
    Explanations

    occurrences of website references and URLs

    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
    363
    +0.11
    0.5%
    430
    +0.10
    0.5%
    139
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.11
    0.02
    107
    +0.10
    0.02
    111
    +0.10
    0.02
    Negative Logits
     carving
    -0.79
     Rabbit
    -0.75
     blurry
    -0.71
     constit
    -0.70
     smelling
    -0.70
     trapping
    -0.70
     sliced
    -0.69
     slit
    -0.68
     snake
    -0.67
     grounding
    -0.66
    POSITIVE LOGITS
    com
    1.69
    org
    1.22
    edu
    1.16
    tumblr
    1.13
    wordpress
    1.13
    sites
    1.11
    co
    1.06
    exe
    1.06
    net
    1.06
    COM
    1.03
    Activations Density 0.015%

    No Known Activations