© 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. 12-RES-JB
    11. 4399
    Prev
    Next
    INDEX
    Explanations

    words related to levels, quantities, and comparisons

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to variable conditions or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    agon
    -0.67
    asket
    -0.65
    iren
    -0.65
    oubt
    -0.63
    drm
    -0.63
    Marsh
    -0.63
     Guard
    -0.62
    goal
    -0.62
    amily
    -0.62
    ournal
    -0.61
    POSITIVE LOGITS
     distances
    1.51
     speeds
    1.49
     levels
    1.48
     heights
    1.47
     depths
    1.41
     scales
    1.39
     rates
    1.38
     intervals
    1.33
     frequencies
    1.32
     intens
    1.31
    Activations Density 0.130%

    No Known Activations