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 3072
    5. 8-RES_FS3072-JB
    6. 2292
    Prev
    Next
    INDEX
    Explanations

    information related to a specific country or specific events related to that country

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    481
    +0.13
    0.6%
    106
    +0.12
    0.6%
    635
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.13
    0.08
    57
    +0.12
    0.07
    461
    +0.11
    0.06
    Negative Logits
     Hitchcock
    -0.77
    iotic
    -0.71
    oway
    -0.70
     Ukip
    -0.70
    ally
    -0.70
     Payton
    -0.70
    fitting
    -0.67
     Ajax
    -0.67
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.67
     Gibbs
    -0.65
    POSITIVE LOGITS
     Jinping
    1.24
     Yuan
    1.20
     Jing
    1.12
     Zhu
    1.10
     Xin
    1.09
    jiang
    1.05
     Guang
    1.02
     yuan
    1.02
    jing
    0.99
     Xia
    0.96
    Activations Density 0.755%

    No Known Activations