© 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. 20113
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geography

    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
    605
    +0.10
    0.5%
    380
    +0.10
    0.5%
    645
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.02
    659
    +0.10
    0.03
    232
    +0.10
    0.02
    Negative Logits
     passports
    -0.71
     dism
    -0.65
     ss
    -0.65
     partName
    -0.63
    âĢ¢âĢ¢
    -0.63
     abund
    -0.60
     withdrawals
    -0.59
     ATL
    -0.57
     Marketable
    -0.57
     EFF
    -0.57
    POSITIVE LOGITS
    mark
    1.02
    marks
    0.98
    nar
    0.89
    nil
    0.86
    lees
    0.85
    enged
    0.84
    ttes
    0.80
    bart
    0.80
    achev
    0.80
    ju
    0.79
    Activations Density 0.052%

    No Known Activations