© 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 12288
    5. 8-RES_FS12288-JB
    6. 1593
    Prev
    Next
    INDEX
    Explanations

    different entities and places mentioned in different documents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    265
    +0.10
    0.5%
    389
    +0.10
    0.5%
    316
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.10
    0.03
    265
    +0.10
    0.03
    389
    +0.10
    0.03
    Negative Logits
    ippy
    -0.80
    untled
    -0.77
    itten
    -0.77
    ilial
    -0.76
    ickle
    -0.74
    NetMessage
    -0.73
    aday
    -0.72
    omsky
    -0.72
    atically
    -0.71
    ambers
    -0.69
    POSITIVE LOGITS
     la
    1.10
     los
    1.06
     las
    0.98
    utsche
    0.96
    cember
    0.89
    utsch
    0.84
    lla
    0.82
    uces
    0.82
     jour
    0.81
     Janeiro
    0.79
    Activations Density 0.044%

    No Known Activations