© 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. 11455
    Prev
    Next
    INDEX
    Explanations

    descriptions related to puzzle boxes and puzzles

    oai_token-act-pair · gpt-3.5-turbo

    references to puzzles and related game mechanics

    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
    exempt
    -0.83
     FSA
    -0.77
    SPA
    -0.74
    avage
    -0.72
    esp
    -0.72
    mosp
    -0.71
    irlf
    -0.70
    ãģ®å®
    -0.70
    lav
    -0.70
    apeake
    -0.69
    POSITIVE LOGITS
     puzzle
    1.91
     puzzles
    1.90
     Puzzles
    1.80
     Puzzle
    1.70
     maze
    1.43
     puzz
    1.33
     maths
    1.33
     solving
    1.32
     Solitaire
    1.30
     clues
    1.30
    Activations Density 0.505%

    No Known Activations