© 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. 2722
    Prev
    Next
    INDEX
    Explanations

    locations or places on a map

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "near."

    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
    xual
    -0.75
    BILL
    -0.66
    Ļ
    -0.63
    Plan
    -0.62
    Accessory
    -0.62
    Organ
    -0.59
    Written
    -0.59
    period
    -0.59
    Percent
    -0.59
    oleon
    -0.59
    POSITIVE LOGITS
    shore
    0.89
     Bethlehem
    0.87
     Calais
    0.85
     campus
    0.84
     shore
    0.84
     Interstate
    0.83
    by
    0.83
     Damascus
    0.82
     midnight
    0.81
     Geneva
    0.79
    Activations Density 0.036%

    No Known Activations