© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20993
    Prev
    Next
    INDEX
    Explanations

    comparative statements indicating something is quantitatively superior or inferior

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a significant distance or disparity

    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
    ortium
    -0.62
     Polo
    -0.59
     Turns
    -0.58
    piracy
    -0.58
     Dice
    -0.57
    ulus
    -0.56
    opoulos
    -0.55
     Revolutionary
    -0.55
     Correction
    -0.55
    ictions
    -0.55
    POSITIVE LOGITS
    med
    1.13
    fetched
    1.07
     outwe
    1.07
     outnumbered
    0.98
     superior
    0.94
     fewer
    0.91
     outweigh
    0.91
     worse
    0.89
    thing
    0.89
     preferable
    0.89
    Activations Density 0.036%

    No Known Activations