© 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. 8-RES-JB
    11. 617
    Prev
    Next
    INDEX
    Explanations

    connections between countries and statistics or rankings

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.77
    elle
    -0.76
    Dispatch
    -0.70
    yrights
    -0.68
    Versions
    -0.65
    perties
    -0.65
    istical
    -0.65
    translation
    -0.65
    informed
    -0.64
     Reporter
    -0.64
    POSITIVE LOGITS
     elsewhere
    0.93
     others
    0.90
     other
    0.87
     possibly
    0.80
     onwards
    0.79
     even
    0.74
     vice
    0.73
     perhaps
    0.73
     Luxembourg
    0.73
     consequently
    0.73
    Activations Density 0.276%

    No Known Activations