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. 1117
    Prev
    Next
    INDEX
    Explanations

    calls to action for participation and support, particularly in projects or causes

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    225
    +0.11
    0.5%
    540
    +0.11
    0.5%
    676
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.11
    0.03
    225
    +0.11
    0.03
    531
    +0.11
    0.03
    Negative Logits
    tein
    -0.75
     Canaver
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.68
    ãĥ¼ãĥĨ
    -0.65
    ãĥ£
    -0.63
     millenn
    -0.63
    atton
    -0.61
     phys
    -0.59
     Beir
    -0.59
    BuyableInstoreAndOnline
    -0.59
    POSITIVE LOGITS
     :)
    0.84
     responsibly
    0.82
    fulness
    0.79
    !
    0.79
     wisely
    0.79
     ;)
    0.74
     TODAY
    0.74
     ðŁĻĤ
    0.71
     :-)
    0.69
     gladly
    0.68
    Activations Density 0.095%

    No Known Activations