© 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. 11345
    Prev
    Next
    INDEX
    Explanations

    information related to sharing and storing digital content

    oai_token-act-pair · gpt-3.5-turbo

    words related to digital content and media sharing functionalities

    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
     Samar
    -0.69
     Advisory
    -0.67
     Crusade
    -0.67
    rance
    -0.64
     Moral
    -0.64
    FML
    -0.64
     condem
    -0.62
    iban
    -0.62
     disclaimer
    -0.61
     pestic
    -0.61
    POSITIVE LOGITS
     efficiently
    1.31
     effortlessly
    1.26
     securely
    1.24
     faster
    1.16
     dynamically
    1.15
     quicker
    1.12
     seamlessly
    1.10
     vertically
    1.07
     instantly
    1.06
     smoothly
    1.05
    Activations Density 0.478%

    No Known Activations