© 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. 11-RES-JB
    11. 281
    Prev
    Next
    INDEX
    Explanations

    comparisons of different quantities, focusing on more or less

    oai_token-act-pair · gpt-3.5-turbo

    comparative terms relating to cost and efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iage
    -0.75
    culosis
    -0.66
    allery
    -0.64
    urtles
    -0.63
     Jackets
    -0.62
    iets
    -0.62
    EStream
    -0.61
    osaurs
    -0.60
     Isle
    -0.59
    vantage
    -0.59
    POSITIVE LOGITS
    -)
    0.85
    )-
    0.85
    -
    0.80
    -[
    0.73
    functional
    0.73
    '-
    0.70
    ]-
    0.70
    -"
    0.70
    dated
    0.69
    sexual
    0.68
    Activations Density 0.139%

    No Known Activations