© 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. 9128
    Prev
    Next
    INDEX
    Explanations

    miscommunication errors and statements that need clarification

    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
    679
    +0.16
    0.8%
    430
    +0.12
    0.6%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.16
    0.11
    679
    +0.12
    0.10
    255
    +0.11
    0.07
    Negative Logits
     earthqu
    -0.83
    ascus
    -0.81
     mosqu
    -0.71
    encia
    -0.70
     devast
    -0.70
     advis
    -0.70
     wre
    -0.69
    ounter
    -0.69
     landfall
    -0.69
     subur
    -0.68
    POSITIVE LOGITS
     Firstly
    1.46
     Suppose
    1.35
     Rather
    1.32
     There
    1.18
     Instead
    1.17
     Unless
    1.16
     If
    1.16
     Regardless
    1.16
     Either
    1.16
     Neither
    1.14
    Activations Density 0.369%

    No Known Activations