© 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. 11998
    Prev
    Next
    INDEX
    Explanations

    words related to writing and composition

    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
    586
    +0.12
    0.5%
    684
    +0.11
    0.5%
    398
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.12
    0.04
    396
    +0.11
    0.03
    393
    +0.10
    0.04
    Negative Logits
    ONSORED
    -0.81
    gdala
    -0.75
    anke
    -0.73
    bucks
    -0.73
    rf
    -0.71
    href
    -0.71
    nels
    -0.71
    ngth
    -0.70
    uni
    -0.70
    yip
    -0.70
    POSITIVE LOGITS
     memoir
    0.87
     screenplay
    0.87
     editor
    0.84
     narration
    0.83
     editors
    0.81
     editing
    0.79
     deaf
    0.75
     interpreter
    0.74
     omission
    0.74
     pencil
    0.73
    Activations Density 0.205%

    No Known Activations