© 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. 8916
    Prev
    Next
    INDEX
    Explanations

    information related to criminal convictions and legal proceedings

    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
    480
    +0.32
    1.6%
    679
    +0.17
    0.8%
    430
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.32
    0.14
    679
    +0.17
    0.13
    430
    +0.14
    0.13
    Negative Logits
    è¦ļéĨĴ
    -0.65
     sustainable
    -0.65
     democrat
    -0.64
     pudding
    -0.62
     defe
    -0.61
     challeng
    -0.61
     mustache
    -0.60
     extinct
    -0.60
     dimensional
    -0.60
    »Ĵ
    -0.59
    POSITIVE LOGITS
     However
    1.24
     Previously
    1.12
     Initially
    1.05
     Though
    1.05
     Instead
    1.04
     But
    1.04
     Although
    1.04
     While
    1.03
     They
    1.03
     Specifically
    0.98
    Activations Density 0.586%

    No Known Activations