© 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. 6-RES-JB
    11. 16902
    Prev
    Next
    INDEX
    Explanations

    words related to daring or attention-seeking actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "stunt" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oice
    -0.70
    ishops
    -0.68
    oan
    -0.67
    inda
    -0.63
     Borders
    -0.61
     Chapters
    -0.61
    lected
    -0.60
     Sett
    -0.60
    och
    -0.60
    ecause
    -0.59
    POSITIVE LOGITS
     stunts
    0.97
     stunt
    0.95
    hered
    0.87
    olicy
    0.81
    strip
    0.77
    woman
    0.77
    nel
    0.75
    monkey
    0.74
     antics
    0.74
    UAL
    0.72
    Activations Density 0.024%

    No Known Activations