© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 12147
    Prev
    Next
    INDEX
    Explanations

    websites or servers mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to websites, servers, and online presence

    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
     racing
    -0.66
     wrench
    -0.64
     fade
    -0.62
     undert
    -0.62
     cris
    -0.61
     shades
    -0.61
     gamb
    -0.60
     struggles
    -0.60
     governors
    -0.60
     courage
    -0.59
    POSITIVE LOGITS
    site
    4.08
    sites
    2.52
    Site
    2.48
     Site
    1.89
     site
    1.87
     sites
    1.50
    bsite
    1.50
    campus
    1.50
     Sites
    1.45
    location
    1.42
    Activations Density 0.013%

    No Known Activations