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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 15703
    Prev
    Next
    INDEX
    Explanations

    phrases related to puzzles

    oai_token-act-pair · gpt-3.5-turbo

    references to puzzles and problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redits
    -0.77
    eatures
    -0.75
    riott
    -0.73
    redit
    -0.70
    ription
    -0.68
    ufact
    -0.68
    rity
    -0.68
    redited
    -0.67
     Liberties
    -0.66
    reditation
    -0.66
    POSITIVE LOGITS
     puzzles
    1.17
     puzzle
    1.08
     solving
    1.00
     Puzzle
    0.93
     solved
    0.90
    uzzle
    0.88
     Puzzles
    0.87
     Pieces
    0.84
    igsaw
    0.84
     puzz
    0.83
    Activations Density 0.035%

    No Known Activations