© 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. 18615
    Prev
    Next
    INDEX
    Explanations

    statements about analogies and comparisons between different concepts

    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
    692
    +0.10
    0.5%
    696
    +0.10
    0.4%
    339
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.10
    0.05
    102
    +0.10
    0.05
    692
    +0.10
    0.03
    Negative Logits
     Universities
    -0.74
     Legions
    -0.73
     directions
    -0.68
     newsletters
    -0.66
     Surve
    -0.65
     Pers
    -0.65
    luster
    -0.64
     Dems
    -0.62
     Kurds
    -0.61
    alities
    -0.61
    POSITIVE LOGITS
     ALWAYS
    0.87
    agraph
    0.81
     capable
    0.78
    typically
    0.78
     indistinguishable
    0.78
     usually
    0.77
     worth
    0.77
    agine
    0.76
     inherently
    0.75
     preferable
    0.74
    Activations Density 0.223%

    No Known Activations