© 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. 3-RES-JB
    11. 17918
    Prev
    Next
    INDEX
    Explanations

    numerical measurements representing sizes, particularly related to diameter

    oai_token-act-pair · gpt-3.5-turbo

    measurements related to size, specifically diameter and radius

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uscript
    -0.81
    ammy
    -0.72
    gotten
    -0.71
    udic
    -0.68
    onto
    -0.68
    unin
    -0.68
    ovie
    -0.67
    inatory
    -0.66
    istine
    -0.66
    Cash
    -0.66
    POSITIVE LOGITS
     diameter
    1.30
     circumference
    1.13
    iameter
    1.08
     radius
    1.00
     diam
    0.87
     cone
    0.77
     dipping
    0.75
     measuring
    0.75
     width
    0.75
     tubing
    0.74
    Activations Density 0.016%

    No Known Activations