© 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. 11-RES-JB
    11. 22060
    Prev
    Next
    INDEX
    Explanations

    symbols or special characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of quantitative data or statistics

    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
     eleph
    -0.91
     tremend
    -0.75
     citiz
    -0.73
     occas
    -0.67
     footing
    -0.61
     downright
    -0.60
    cius
    -0.60
    ò
    -0.59
    aturdays
    -0.59
     sucker
    -0.59
    POSITIVE LOGITS
    Appearances
    1.09
    Contents
    1.06
    edit
    1.00
    Background
    0.91
    Gameplay
    0.90
    History
    0.89
    Appearance
    0.89
    Trivia
    0.88
    Notable
    0.86
    Overview
    0.86
    Activations Density 0.126%

    No Known Activations