© 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. 21875
    Prev
    Next
    INDEX
    Explanations

    trailing punctuation and symbols like 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of high activation values, indicating strong emphasis or excitement

    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
     eleph
    -0.95
     CONC
    -0.83
     Carnegie
    -0.81
     Heritage
    -0.78
     crowds
    -0.78
     crocod
    -0.77
     Mobil
    -0.77
     excav
    -0.76
     UNESCO
    -0.76
     photograp
    -0.76
    POSITIVE LOGITS
    Reply
    2.00
    Anonymous
    1.85
    Edited
    1.73
    anon
    1.68
    RAW
    1.67
    Quote
    1.66
    Reviewer
    1.64
    Rated
    1.64
    reply
    1.63
    EDIT
    1.62
    Activations Density 0.266%

    No Known Activations