© 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. 6566
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency-related terms

    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
    +0.27
    1.2%
    481
    +0.16
    0.8%
    314
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.27
    0.07
    406
    +0.16
    0.07
    232
    +0.13
    0.06
    Negative Logits
     nationally
    -0.70
     outgoing
    -0.64
     prevail
    -0.63
     infringing
    -0.62
     morphine
    -0.61
     politically
    -0.61
     spoken
    -0.61
     internationally
    -0.61
     scratch
    -0.60
     heirs
    -0.59
    POSITIVE LOGITS
    uff
    1.05
    andra
    1.05
    je
    1.04
    unda
    1.04
    ote
    1.04
    ongo
    1.04
    cia
    1.03
    olor
    1.03
    icz
    1.01
    cs
    1.01
    Activations Density 0.293%

    No Known Activations