© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 6605
    Prev
    Next
    INDEX
    Explanations

    historical references and technical information related to government regulations and technology

    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
    481
    +0.10
    0.5%
    679
    +0.10
    0.4%
    540
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.10
    0.04
    762
    +0.10
    0.04
    349
    +0.10
    0.03
    Negative Logits
    steen
    -0.64
    ococ
    -0.63
    enhagen
    -0.60
     Correct
    -0.60
    itone
    -0.58
     Barg
    -0.58
    angan
    -0.57
    bestos
    -0.56
    CHAT
    -0.56
    rection
    -0.56
    POSITIVE LOGITS
     besides
    0.86
     except
    0.85
     surveyed
    0.79
     whatsoever
    0.76
     nationwide
    0.74
     nowadays
    0.73
     imaginable
    0.68
     vying
    0.67
     alike
    0.67
     ever
    0.67
    Activations Density 0.173%

    No Known Activations