© 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. 20633
    Prev
    Next
    INDEX
    Explanations

    numerical values matching a specific format (e.g., 18 acres, 486-219-593)

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their variations throughout the text

    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
     nodd
    -0.79
     quir
    -0.70
     spitting
    -0.68
     sucker
    -0.66
     crunch
    -0.65
     refined
    -0.64
     imp
    -0.62
     electr
    -0.62
     mandate
    -0.62
     detect
    -0.62
    POSITIVE LOGITS
    ,,
    1.62
    ,,,,
    1.42
    ,.
    1.34
     ,
    1.33
    Newsletter
    1.23
    :,
    1.21
    ,,,,,,,,
    1.21
    (),
    1.15
    ?,
    1.14
    ,...
    1.14
    Activations Density 0.151%

    No Known Activations