© 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. 8142
    Prev
    Next
    INDEX
    Explanations

    text related to occupational health programs for astronauts

    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
    213
    +0.13
    0.6%
    637
    +0.12
    0.6%
    336
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.13
    0.02
    637
    +0.12
    0.02
    28
    +0.11
    0.02
    Negative Logits
    lihood
    -0.96
    lings
    -0.76
     Resurrection
    -0.71
     Genesis
    -0.71
     Presbyter
    -0.67
    nings
    -0.66
     Rabb
    -0.65
    ãĥĥãĤ¯
    -0.64
     filling
    -0.64
    querque
    -0.62
    POSITIVE LOGITS
    ISM
    1.21
    IZE
    1.18
    IME
    1.18
    INC
    1.16
    OPER
    1.16
    OF
    1.12
    ODUCT
    1.07
    INTER
    1.07
    IOR
    1.06
    ICE
    1.05
    Activations Density 0.013%

    No Known Activations