© 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. 12-RES-JB
    11. 3534
    Prev
    Next
    INDEX
    Explanations

    names related to football positions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    quotes or direct speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exting
    -0.98
    Þ
    -0.94
    FORE
    -0.93
    è¦ļéĨĴ
    -0.87
    DragonMagazine
    -0.86
    artisan
    -0.86
     Feminist
    -0.84
    MSN
    -0.84
     Citiz
    -0.83
     guiActiveUn
    -0.82
    POSITIVE LOGITS
     Coach
    1.13
     [
    1.11
     guys
    1.10
     offensively
    0.98
     scrimmage
    0.98
    Coach
    0.94
     everybody
    0.92
     coaches
    0.90
     adversity
    0.90
     defensively
    0.90
    Activations Density 0.491%

    No Known Activations