© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 41567
    Prev
    Next
    INDEX
    Explanations

    instances of the word "told."

    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
    679
    +0.11
    0.5%
    257
    +0.10
    0.4%
    417
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.11
    0.04
    257
    +0.10
    0.04
    426
    +0.10
    0.03
    Negative Logits
     ILCS
    -0.80
    aband
    -0.76
    Interstitial
    -0.75
    isol
    -0.75
    illion
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
    é¾įåĸļ士
    -0.69
    ample
    -0.68
    agement
    -0.66
     sidx
    -0.66
    POSITIVE LOGITS
     reporters
    1.22
     BuzzFeed
    1.01
     HuffPost
    1.00
     BBC
    0.88
     VICE
    0.88
     Politico
    0.88
     me
    0.87
     Guardian
    0.86
     Newsweek
    0.84
     CNBC
    0.84
    Activations Density 0.040%

    No Known Activations