© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11108
    Prev
    Next
    INDEX
    Explanations

    paragraphs or sentences that end with punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings, particularly those marked by punctuation

    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
    arily
    -0.94
    inking
    -0.92
    userc
    -0.82
     planners
    -0.82
     experimentation
    -0.81
     stocking
    -0.81
     planning
    -0.78
     sensitive
    -0.77
     regress
    -0.76
     drift
    -0.76
    POSITIVE LOGITS
     Il
    1.12
     Pour
    1.10
     Si
    1.04
     Ãľ
    1.02
     Les
    1.01
     Amen
    1.01
     Ces
    1.00
     »
    1.00
     Ce
    1.00
     Et
    1.00
    Activations Density 0.043%

    No Known Activations