© 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. 12134
    Prev
    Next
    INDEX
    Explanations

    proper nouns and locations, specifically those related to sports and politics

    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
    373
    +0.26
    1.3%
    747
    +0.10
    0.5%
    20
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.26
    -0.01
    232
    +0.10
    0.03
    613
    +0.10
    0.03
    Negative Logits
     favors
    -0.58
     Jinn
    -0.56
     scraps
    -0.53
     UFOs
    -0.51
     UFO
    -0.51
     Ved
    -0.50
     sher
    -0.50
     constitu
    -0.49
     Favor
    -0.48
     synopsis
    -0.48
    POSITIVE LOGITS
    wagen
    0.89
    helm
    0.78
    ggle
    0.76
    gart
    0.76
    wart
    0.75
    leck
    0.71
    ilda
    0.71
    otyp
    0.68
    amac
    0.67
    lich
    0.66
    Activations Density 0.115%

    No Known Activations