© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 22928
    Prev
    Next
    INDEX
    Explanations

    instances where something is being finished or concluded, often related to seasons, games, matches, or years

    oai_token-act-pair · gpt-3.5-turbo

    references to seasons in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     persists
    -0.71
     persisted
    -0.63
     circulation
    -0.60
    outer
    -0.58
     manifests
    -0.58
    ibles
    -0.57
    sect
    -0.57
     swall
    -0.56
    ibilities
    -0.55
     diaper
    -0.54
    POSITIVE LOGITS
     knowing
    0.95
     squarely
    0.91
     differently
    0.84
     undefeated
    0.81
     cautiously
    0.80
     unsc
    0.78
     expecting
    0.78
     believing
    0.76
     prematurely
    0.73
     unprepared
    0.73
    Activations Density 0.294%

    No Known Activations