© 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 49152
    9. 8-RES_FS49152-JB
    11. 43478
    Prev
    Next
    INDEX
    Explanations

    key terms related to scheduled events or conditions in a process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    502
    +0.10
    0.5%
    605
    +0.10
    0.5%
    685
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.10
    0.05
    49
    +0.10
    0.06
    502
    +0.10
    0.05
    Negative Logits
     Allaah
    -0.69
    ailability
    -0.69
     Bronze
    -0.65
     mixer
    -0.64
     ether
    -0.63
     Hof
    -0.62
     steroid
    -0.60
     capacitor
    -0.58
     Fey
    -0.57
    eatures
    -0.56
    POSITIVE LOGITS
     emulate
    0.78
    abouts
    0.78
     deems
    0.75
    should
    0.73
    igraph
    0.73
    intend
    0.71
     cherish
    0.70
    tre
    0.69
     entails
    0.69
    isse
    0.68
    Activations Density 0.585%

    No Known Activations