© 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. 8-RES-JB
    6. 2502
    Prev
    Next
    INDEX
    Explanations

    people or groups gathering or protesting outside various locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "outside" in contexts related to protests or gatherings

    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
    oleon
    -0.83
    anche
    -0.80
    ppe
    -0.77
    XX
    -0.75
    oka
    -0.71
    Lay
    -0.71
    Reply
    -0.70
    geist
    -0.70
    information
    -0.70
    feature
    -0.69
    POSITIVE LOGITS
     Staples
    0.73
     Sunset
    0.71
     patio
    0.71
     perimeter
    0.69
     Downing
    0.69
     Costco
    0.69
     town
    0.69
     Damascus
    0.68
     Hogwarts
    0.68
     parliament
    0.68
    Activations Density 0.033%

    No Known Activations