© 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. 10-RES-JB
    11. 9924
    Prev
    Next
    INDEX
    Explanations

    words related to mysteries or puzzles

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to mystery and intrigue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    attery
    -0.86
    baugh
    -0.81
    redits
    -0.76
    uci
    -0.76
    odium
    -0.74
    enses
    -0.73
    reditation
    -0.72
    ivals
    -0.71
    ornia
    -0.70
    ovie
    -0.70
    POSITIVE LOGITS
     solved
    1.39
     unsolved
    1.18
     puzzle
    1.12
     solving
    1.09
     puzzles
    1.06
     mystery
    0.95
     solve
    0.94
     Puzzles
    0.89
     unravel
    0.89
     surrounds
    0.86
    Activations Density 0.057%

    No Known Activations