© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 19661
    Prev
    Next
    INDEX
    Explanations

    references to puzzle-related activities and objects

    oai_token-act-pair · gpt-3.5-turbo

    references to puzzles and puzzle-solving mechanics in games

    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
    riott
    -0.70
    rity
    -0.67
    EVA
    -0.66
     Liberties
    -0.66
    redit
    -0.64
    rolog
    -0.64
     disclaim
    -0.64
    ufact
    -0.64
    redits
    -0.63
    ulf
    -0.63
    POSITIVE LOGITS
     puzzles
    1.18
     puzzle
    1.15
     solving
    1.07
     Puzzle
    0.99
    igsaw
    0.94
     Puzzles
    0.91
    uzzle
    0.90
     solved
    0.85
     Pieces
    0.83
     maze
    0.83
    Activations Density 0.098%

    No Known Activations