© 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. 11-RES-JB
    11. 15025
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical attributes and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    elements related to quality, design, and structure

    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
    noticed
    -0.57
     Said
    -0.57
    AAA
    -0.56
     fanc
    -0.55
     Notting
    -0.54
    Missing
    -0.54
    arently
    -0.54
    OLD
    -0.53
     Was
    -0.53
     alleged
    -0.52
    POSITIVE LOGITS
     allow
    1.37
     enable
    1.36
     signify
    1.32
     ensure
    1.32
     stimulate
    1.32
     enhance
    1.32
     facilitate
    1.30
     propel
    1.30
     create
    1.29
     provide
    1.28
    Activations Density 0.581%

    No Known Activations