© 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. 7684
    Prev
    Next
    INDEX
    Explanations

    phrases related to dealing with challenges or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    articles and quantifiers like "a" and "lots."

    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
    Contents
    -0.73
    %:
    -0.70
    Images
    -0.69
     Released
    -0.67
    antic
    -0.66
     unsurprisingly
    -0.66
     Shares
    -0.64
     Annotations
    -0.64
     additionally
    -0.63
     Amid
    -0.63
    POSITIVE LOGITS
     lot
    1.52
     bunch
    1.27
     guy
    1.19
     really
    1.17
     couple
    1.08
     little
    1.04
     tremendous
    1.02
     whole
    1.02
     pretty
    0.97
     very
    0.97
    Activations Density 0.257%

    No Known Activations