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 49152
    5. 8-RES_FS49152-JB
    6. 41194
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mc"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    659
    +0.16
    0.7%
    19
    +0.10
    0.5%
    251
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.02
    251
    +0.10
    0.01
    376
    +0.10
    0.01
    Negative Logits
    ãĥĥãĥĪ
    -0.78
     unprotected
    -0.77
     Gemini
    -0.75
    ãĥ¼ãĥĨ
    -0.74
    ãĥ³ãĤ¸
    -0.71
     CBI
    -0.71
    éĹĺ
    -0.69
     deaf
    -0.69
     mistaken
    -0.66
     heartbeat
    -0.65
    POSITIVE LOGITS
    intosh
    1.42
    Afee
    1.36
    Leod
    1.20
    artney
    1.20
    donald
    1.15
    Connell
    1.07
    Donald
    1.05
    Lean
    1.04
    owan
    1.04
    Kin
    0.99
    Activations Density 0.006%

    No Known Activations