© 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. 10-RES-JB
    11. 11280
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a question mark

    oai_token-act-pair · gpt-3.5-turbo

    repeated punctuation marks and symbols that may signify a pattern or emphasis in 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
     segreg
    -0.77
     tremend
    -0.71
     Sabha
    -0.70
     dispers
    -0.70
     Cycl
    -0.70
     Mous
    -0.69
     assemb
    -0.68
     sling
    -0.68
     CMS
    -0.68
     Alc
    -0.66
    POSITIVE LOGITS
    ľ
    1.71
    ¬
    1.26
    ¦
    1.22
    Ľ
    1.21
    ł
    1.20
    ¼
    1.15
    Ń
    1.14
    ª
    1.12
    ¡
    1.12
    º
    1.11
    Activations Density 0.283%

    No Known Activations