© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 467
    Prev
    Next
    INDEX
    Explanations

    words related to puzzles and puzzle-solving

    oai_token-act-pair · gpt-3.5-turbo

    references to puzzles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ml
    -0.70
    redits
    -0.69
    ributes
    -0.69
    ribute
    -0.67
    ript
    -0.66
    estial
    -0.66
    artney
    -0.65
    ankind
    -0.65
    ather
    -0.64
    rol
    -0.64
    POSITIVE LOGITS
     puzzles
    1.40
     puzzle
    1.38
    ĸļ
    1.16
     Puzzles
    1.11
     Puzzle
    1.10
     puzz
    1.01
     Puzz
    0.99
     solving
    0.97
     puzzling
    0.86
     solved
    0.86
    Activations Density 0.007%

    No Known Activations