© 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. 11-RES-JB
    11. 2820
    Prev
    Next
    INDEX
    Explanations

    text in a specific format with the character "Ċ" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and performance metrics in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     eleph
    -0.87
     proport
    -0.85
     citiz
    -0.83
    aditional
    -0.82
     hemor
    -0.82
     exting
    -0.78
     tremend
    -0.78
     undermin
    -0.78
     exha
    -0.76
     occas
    -0.72
    POSITIVE LOGITS
    Thumbnail
    0.88
    ³³³
    0.86
    ↵
    0.83
    zinski
    0.83
    DragonMagazine
    0.79
    Wide
    0.79
    Fans
    0.77
    Jimmy
    0.76
    PK
    0.75
    Coach
    0.75
    Activations Density 0.298%

    No Known Activations