© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3296
    Prev
    Next
    INDEX
    Explanations

    phrases where something will or will not happen in the future

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "won't" as well as its variations and contexts within the document

    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
     Jem
    -0.65
     shack
    -0.65
     Roose
    -0.64
     silhou
    -0.63
     chained
    -0.63
     Wilmington
    -0.62
     backdrop
    -0.62
     intersect
    -0.61
     Erit
    -0.61
     Laurent
    -0.60
    POSITIVE LOGITS
    iversary
    1.11
    ï¸ı
    1.01
    uable
    0.91
    $
    0.90
    cation
    0.86
    arant
    0.85
    cade
    0.84
    ulty
    0.84
    ship
    0.84
    tarians
    0.83
    Activations Density 0.055%

    No Known Activations