© 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 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. 3-RES-JB
    11. 24316
    Prev
    Next
    INDEX
    Explanations

    references to physical measurements, specifically focusing on square feet

    oai_token-act-pair · gpt-3.5-turbo

    measurements related to square footage

    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
    nat
    -0.66
     Wein
    -0.65
     Nim
    -0.62
     Lauder
    -0.62
     Sirius
    -0.61
    oleon
    -0.59
     Crus
    -0.58
     Mothers
    -0.58
    KEN
    -0.57
     tyr
    -0.57
    POSITIVE LOGITS
    elsius
    0.94
    spread
    0.77
    merce
    0.75
    scl
    0.74
    galitarian
    0.72
    abytes
    0.72
    Compat
    0.71
    awatts
    0.70
    glass
    0.68
    undred
    0.67
    Activations Density 0.034%

    No Known Activations