© 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 24576
    9. 8-RES_FS24576-JB
    11. 1993
    Prev
    Next
    INDEX
    Explanations

    phrases related to monetary or financial topics

    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
    +0.13
    0.6%
    291
    +0.09
    0.4%
    745
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.13
    0.03
    406
    +0.09
    0.03
    326
    +0.09
    0.03
    Negative Logits
    ynski
    -0.74
    kar
    -0.74
    ivia
    -0.73
    inyl
    -0.71
    idential
    -0.70
    isal
    -0.70
    Solution
    -0.69
    ARC
    -0.69
    heny
    -0.67
     Citation
    -0.67
    POSITIVE LOGITS
     eyed
    0.97
     noses
    0.83
     nose
    0.80
     ears
    0.76
     tail
    0.76
     paw
    0.76
     tails
    0.76
    etheless
    0.76
     egg
    0.74
     paws
    0.74
    Activations Density 0.151%

    No Known Activations