© 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. 1028
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific punctuation marks or signs

    oai_token-act-pair · gpt-3.5-turbo

    parentheses or references to asides within the text

    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
     bows
    -0.74
     comparisons
    -0.73
     joints
    -0.70
     bow
    -0.70
     forests
    -0.69
     chats
    -0.66
     Champ
    -0.66
     grips
    -0.66
     Aires
    -0.66
     evening
    -0.66
    POSITIVE LOGITS
    mostly
    1.71
    albeit
    1.67
    possibly
    1.62
    sic
    1.58
    almost
    1.57
    sometimes
    1.53
    literally
    1.51
    usually
    1.50
    insert
    1.48
    often
    1.47
    Activations Density 0.102%

    No Known Activations