© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19383
    Prev
    Next
    INDEX
    Explanations

    words related to changes or modifications

    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
    447
    +0.23
    1.0%
    665
    +0.11
    0.5%
    656
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.23
    0.05
    125
    +0.11
    0.04
    217
    +0.10
    0.03
    Negative Logits
    AIDS
    -0.63
     Flavoring
    -0.58
     Gathering
    -0.57
     Fein
    -0.57
    Found
    -0.57
    76561
    -0.56
    Phones
    -0.55
     Nile
    -0.55
     infections
    -0.55
    Torrent
    -0.54
    POSITIVE LOGITS
     accordingly
    0.96
    uled
    0.81
     slightly
    0.80
     administr
    0.79
     drastically
    0.77
     appropriately
    0.75
     considerably
    0.73
     indefinitely
    0.71
     dramatically
    0.71
     temporarily
    0.71
    Activations Density 0.149%

    No Known Activations