© 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. 8525
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or entities named "Cross."

    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
    99
    +0.14
    0.6%
    686
    +0.11
    0.5%
    29
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.14
    0.02
    13
    +0.11
    0.02
    342
    +0.09
    0.01
    Negative Logits
    RAG
    -0.75
     Gupta
    -0.72
     UCH
    -0.71
    ENCY
    -0.67
    UGH
    -0.67
    ccording
    -0.64
    rolog
    -0.64
    acious
    -0.64
    ailable
    -0.63
     contagious
    -0.63
    POSITIVE LOGITS
    roads
    1.51
    bones
    1.16
    bow
    1.04
    bows
    1.03
    es
    1.02
    Fit
    0.92
    rail
    0.91
     Sakuya
    0.90
    word
    0.83
    fax
    0.83
    Activations Density 0.026%

    No Known Activations