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

    Neuronpedia

    Jacobian LensNEW
    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 24576
    9. 8-RES_FS24576-JB
    11. 5885
    Prev
    Next
    INDEX
    Explanations

    the word "there" occurring in sentences

    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
    373
    +0.14
    0.7%
    287
    +0.14
    0.6%
    494
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.14
    0.11
    494
    +0.14
    0.07
    94
    +0.10
    0.07
    Negative Logits
     Slayer
    -0.62
     Doom
    -0.60
    ship
    -0.59
    ITS
    -0.58
     Throne
    -0.57
     cup
    -0.57
     cub
    -0.57
    full
    -0.57
    crow
    -0.56
     throne
    -0.55
    POSITIVE LOGITS
    abouts
    1.55
    upon
    1.12
    etheless
    0.94
    after
    0.90
    fore
    0.86
    currently
    0.80
    FORE
    0.78
     are
    0.77
    ngth
    0.74
    zbollah
    0.73
    Activations Density 0.116%

    No Known Activations