© 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. 6437
    Prev
    Next
    INDEX
    Explanations

    phrases related to emphasizing a point strongly

    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
    567
    +0.12
    0.6%
    468
    +0.11
    0.5%
    240
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    567
    +0.12
    0.04
    374
    +0.11
    0.03
    468
    +0.11
    0.04
    Negative Logits
    esi
    -0.62
    theless
    -0.59
     Flavoring
    -0.58
    wire
    -0.58
    question
    -0.57
     grunt
    -0.56
    throp
    -0.55
    ãģ£
    -0.54
     glances
    -0.54
     Frie
    -0.53
    POSITIVE LOGITS
    othe
    1.18
    bered
    1.17
    apy
    1.06
    othes
    0.94
    aps
    0.88
    oths
    0.87
    arer
    0.86
    oner
    0.79
    arin
    0.75
    pping
    0.74
    Activations Density 0.056%

    No Known Activations