© 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. 13676
    Prev
    Next
    INDEX
    Explanations

    pages, chapters, and sections in a document

    oai_token-act-pair · gpt-3.5-turbo

    formatting related to chapter navigation in a document

    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
     bir
    -0.70
    emouth
    -0.68
     partnering
    -0.67
     unilaterally
    -0.65
     ambassadors
    -0.65
     rigging
    -0.63
     administering
    -0.62
     seizing
    -0.62
    tle
    -0.61
     disadvant
    -0.61
    POSITIVE LOGITS
     Page
    1.30
     Contents
    1.24
     Chapter
    1.17
     PAGE
    1.14
    Page
    1.12
    Chapter
    1.09
    cerpt
    1.06
     Pages
    1.06
     page
    1.05
    Next
    1.05
    Activations Density 0.151%

    No Known Activations