© 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. 14103
    Prev
    Next
    INDEX
    Explanations

    words related to burning or fire

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of burning or destruction

    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
     Slam
    -0.70
    ele
    -0.69
     Ake
    -0.67
    maid
    -0.67
    alian
    -0.67
    gravity
    -0.65
    DonaldTrump
    -0.63
    DragonMagazine
    -0.62
    schild
    -0.62
    yip
    -0.61
    POSITIVE LOGITS
     hotter
    1.14
    ished
    1.11
    ishing
    1.07
     brightly
    1.00
    ishes
    0.96
     ashes
    0.94
     burning
    0.92
     alive
    0.87
     bridges
    0.87
     brighter
    0.85
    Activations Density 0.067%

    No Known Activations