© 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. 7594
    Prev
    Next
    INDEX
    Explanations

    names 'Rud' and its variants in the text

    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
    699
    +0.12
    0.5%
    357
    +0.11
    0.5%
    339
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.12
    0.01
    326
    +0.11
    0.01
    699
    +0.10
    0.01
    Negative Logits
     ILCS
    -0.78
     Ago
    -0.74
     Izan
    -0.64
     Sunshine
    -0.63
    ãĥĩãĤ£
    -0.62
     plates
    -0.60
    merce
    -0.59
    ãĤ¿
    -0.59
    pora
    -0.59
    OOL
    -0.58
    POSITIVE LOGITS
    imentary
    1.33
    olf
    1.08
    der
    1.06
    itionally
    1.00
    imental
    0.94
    olph
    0.93
    eness
    0.93
    enthal
    0.89
    iments
    0.89
    esc
    0.88
    Activations Density 0.023%

    No Known Activations