© 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. 11-RES-JB
    11. 15729
    Prev
    Next
    INDEX
    Explanations

    words related to burning or fire

    oai_token-act-pair · gpt-3.5-turbo

    references to burning or destruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Slam
    -0.70
    maid
    -0.66
    ortment
    -0.65
    ele
    -0.64
    schild
    -0.64
    gravity
    -0.63
    ror
    -0.60
    padding
    -0.59
     BRE
    -0.59
    BUT
    -0.59
    POSITIVE LOGITS
    ished
    1.14
     hotter
    1.09
     brightly
    1.06
    ishing
    1.04
    ishes
    0.95
     bridges
    0.88
     ashes
    0.87
     burning
    0.83
    ishable
    0.83
     alive
    0.83
    Activations Density 0.088%

    No Known Activations