© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12678
    Prev
    Next
    INDEX
    Explanations

    patterns or solutions

    oai_token-act-pair · gpt-3.5-turbo

    concepts associated with patterns, solutions, and challenges across various contexts

    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
    Returns
    -0.78
    laughs
    -0.67
    Has
    -0.64
    Attempts
    -0.62
    Was
    -0.62
    needs
    -0.60
     Uses
    -0.59
     Fixes
    -0.58
    uther
    -0.58
    ATES
    -0.58
    POSITIVE LOGITS
     aren
    1.34
     are
    1.28
     weren
    1.23
     vary
    1.19
     were
    1.11
     differ
    1.07
     seem
    1.06
     themselves
    1.04
     comprise
    1.00
     constitute
    0.99
    Activations Density 0.314%

    No Known Activations