© 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. 8-RES-JB
    11. 11312
    Prev
    Next
    INDEX
    Explanations

    parentheses at the beginning or end of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the presence of parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tack
    -0.70
     dow
    -0.69
     entitle
    -0.67
     hoop
    -0.67
     Maced
    -0.66
     Dimensions
    -0.66
     Elys
    -0.65
     maker
    -0.64
     margin
    -0.64
     comparisons
    -0.63
    POSITIVE LOGITS
    ...)
    1.42
    sic
    1.40
    âĢ¦)
    1.33
    possibly
    1.31
    mostly
    1.29
    partial
    1.25
    formerly
    1.23
    usually
    1.23
    insert
    1.21
    ?)
    1.21
    Activations Density 0.105%

    No Known Activations