© 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. 10-RES-JB
    11. 7976
    Prev
    Next
    INDEX
    Explanations

    references to the name "Messi."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Meson" and related particle physics concepts

    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
    FUL
    -0.67
    ists
    -0.63
     void
    -0.60
    istically
    -0.59
     anthem
    -0.58
     whims
    -0.58
     restitution
    -0.57
     ATP
    -0.56
     payable
    -0.56
     Fulton
    -0.54
    POSITIVE LOGITS
    quite
    1.49
    hing
    1.32
    opot
    1.23
    meric
    1.20
    hed
    1.13
    hes
    1.12
    elf
    1.10
    coe
    1.06
    chel
    1.05
    olithic
    1.03
    Activations Density 0.037%

    No Known Activations