© 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. 16727
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to qualities, characteristics, or things that make something notable or special

    oai_token-act-pair · gpt-3.5-turbo

    recurring themes of what constitutes greatness or uniqueness

    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
     confines
    -0.75
     unfocusedRange
    -0.72
    200000
    -0.64
    colo
    -0.62
    luaj
    -0.62
    multiple
    -0.62
    ertation
    -0.62
    translation
    -0.61
    0000000
    -0.61
    unknown
    -0.61
    POSITIVE LOGITS
     tick
    1.19
     unique
    1.12
     special
    1.08
     distinctive
    1.06
     exceptional
    1.03
     remarkable
    1.02
     noteworthy
    1.02
     attractive
    1.01
     resonate
    0.99
     memorable
    0.99
    Activations Density 0.112%

    No Known Activations