© 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. 11261
    Prev
    Next
    INDEX
    Explanations

    mathematical and physical science terms related to calculations, measurements, and units

    oai_token-act-pair · gpt-3.5-turbo

    scientific measurements and parameters related to physical properties

    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
     Nurs
    -0.68
     reinvent
    -0.67
     Alma
    -0.67
     goodbye
    -0.66
    uitous
    -0.66
     Mirage
    -0.64
     Cyrus
    -0.63
     laz
    -0.63
     Wond
    -0.63
     voices
    -0.63
    POSITIVE LOGITS
     ratio
    1.17
    max
    1.12
    reshold
    1.11
     Ratio
    1.11
     coefficient
    1.10
     ratios
    1.08
    ensity
    1.08
    PI
    1.05
    PM
    1.05
     =
    1.00
    Activations Density 0.148%

    No Known Activations