© 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. 10-RES-JB
    11. 1130
    Prev
    Next
    INDEX
    Explanations

    height measurements in feet and inches

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations of height and weight measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     observing
    -0.64
     eas
    -0.64
     Hann
    -0.64
     Lanka
    -0.62
     Surv
    -0.62
     stale
    -0.60
     une
    -0.60
     liking
    -0.59
     Kad
    -0.59
     reconciliation
    -0.59
    POSITIVE LOGITS
    foot
    1.22
    feet
    1.13
    year
    1.12
    star
    1.08
    figure
    1.07
    inch
    1.06
    month
    1.02
    digit
    0.99
    months
    0.96
    stars
    0.96
    Activations Density 0.057%

    No Known Activations