© 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. 7528
    Prev
    Next
    INDEX
    Explanations

    specific words that contain the substring "doub"

    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
    421
    +0.11
    0.5%
    540
    +0.10
    0.5%
    651
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.01
    651
    +0.10
    0.01
    503
    +0.10
    0.01
    Negative Logits
    ĸļ
    -0.69
     Provided
    -0.64
    ODUCT
    -0.63
    anwhile
    -0.63
     Polo
    -0.62
     Advisor
    -0.61
     Occupations
    -0.61
     Afric
    -0.61
     Adv
    -0.61
     NETWORK
    -0.61
    POSITIVE LOGITS
    ters
    1.49
    ting
    1.42
    ter
    1.19
    ly
    1.14
    ted
    1.09
    tered
    1.07
    ts
    1.01
    tering
    0.96
    etooth
    0.95
    te
    0.94
    Activations Density 0.029%

    No Known Activations