© 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. 10-RES-JB
    11. 18639
    Prev
    Next
    INDEX
    Explanations

    names of game creators

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that end with punctuation marks

    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
     pse
    -0.86
     anyway
    -0.80
    umably
    -0.75
     attrition
    -0.71
     depreciation
    -0.69
     presumably
    -0.69
     defe
    -0.68
     libel
    -0.68
     advis
    -0.68
    ems
    -0.67
    POSITIVE LOGITS
     Featuring
    1.69
     Whether
    1.50
     Each
    1.46
     Designed
    1.41
     Along
    1.36
     Located
    1.35
     Includes
    1.34
     Inspired
    1.32
     Explore
    1.31
     With
    1.30
    Activations Density 0.289%

    No Known Activations