© 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. 0-RES-JB
    11. 5283
    Prev
    Next
    INDEX
    Explanations

    entries or mentions in a piece of text

    oai_token-act-pair · gpt-3.5-turbo

    references to entries and submissions in a contest or competition context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cord
    -0.79
    shield
    -0.69
    OUGH
    -0.68
    peria
    -0.63
    pport
    -0.63
     paralyzed
    -0.62
    usa
    -0.61
     Slim
    -0.61
     Wasserman
    -0.61
    instein
    -0.59
    POSITIVE LOGITS
     entries
    3.79
     entrants
    2.07
     entry
    1.88
     submissions
    1.72
    Entry
    1.57
     Entry
    1.54
     registrations
    1.52
     installments
    1.46
     listings
    1.42
     nominations
    1.37
    Activations Density 0.013%

    No Known Activations