© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10816
    Prev
    Next
    INDEX
    Explanations

    names of countries and geographical locations

    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
    95
    +0.12
    0.5%
    374
    +0.11
    0.5%
    362
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.12
    0.03
    373
    +0.11
    -0.01
    95
    +0.11
    0.02
    Negative Logits
    ¶
    -0.92
    ername
    -0.86
    haar
    -0.81
    words
    -0.80
    ascript
    -0.80
    ĺħ
    -0.78
    talk
    -0.77
    ategory
    -0.76
    olean
    -0.75
    ndum
    -0.75
    POSITIVE LOGITS
     Zeus
    0.78
    isSpecialOrderable
    0.75
    soType
    0.70
     postwar
    0.65
    ItemThumbnailImage
    0.65
    Buyable
    0.65
    BuyableInstoreAndOnline
    0.64
     Came
    0.63
     stricken
    0.62
     tilt
    0.61
    Activations Density 0.064%

    No Known Activations