© 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. 1426
    Prev
    Next
    INDEX
    Explanations

    financial and statistical information

    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
    4
    +0.13
    0.6%
    668
    +0.12
    0.6%
    79
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    668
    +0.13
    0.04
    366
    +0.12
    0.03
    4
    +0.10
    0.04
    Negative Logits
     spont
    -0.75
     pamph
    -0.73
    00200000
    -0.69
     lectures
    -0.69
    actions
    -0.67
     messenger
    -0.66
     improvised
    -0.64
     lessons
    -0.64
    opsy
    -0.62
    istrates
    -0.62
    POSITIVE LOGITS
     surpass
    1.21
     surpassed
    1.07
     unbeaten
    1.04
    Ranked
    1.02
     outper
    1.00
     unbeat
    0.99
    ranked
    0.97
     topped
    0.97
    Rank
    0.95
     ranking
    0.93
    Activations Density 0.335%

    No Known Activations