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. 11469
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "the"

    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
    393
    +0.19
    0.9%
    362
    +0.13
    0.6%
    385
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.19
    0.04
    362
    +0.13
    0.04
    393
    +0.10
    0.03
    Negative Logits
    Lago
    -0.66
    seek
    -0.65
     reminis
    -0.63
    oster
    -0.62
     aloud
    -0.60
     unsuccessfully
    -0.59
    puff
    -0.59
    FontSize
    -0.59
    ãĥĺ
    -0.58
    arry
    -0.58
    POSITIVE LOGITS
     brunt
    1.07
     opportunity
    1.04
     same
    1.03
     idea
    1.01
     requisite
    0.99
     slightest
    0.98
     gist
    0.96
     hardest
    0.94
     easiest
    0.93
     latest
    0.92
    Activations Density 0.078%

    No Known Activations