© 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. 3-RES-JB
    11. 4347
    Prev
    Next
    INDEX
    Explanations

    words related to puzzles and puzzle-solving

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with puzzles and puzzle-solving activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redits
    -0.72
    ibaba
    -0.70
    treated
    -0.68
    umption
    -0.67
    oln
    -0.67
    rity
    -0.67
    redited
    -0.65
    rogens
    -0.64
    estial
    -0.64
    rol
    -0.64
    POSITIVE LOGITS
     puzzle
    1.17
     puzzles
    1.15
    ĸļ
    1.08
     solving
    0.92
     Puzzle
    0.91
     puzz
    0.85
     Puzz
    0.83
     Puzzles
    0.81
     solved
    0.79
     Shack
    0.76
    Activations Density 0.008%

    No Known Activations