© 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. 21004
    Prev
    Next
    INDEX
    Explanations

    height measurements in feet and inches

    oai_token-act-pair · gpt-3.5-turbo

    specific numeric values or symbols in text

    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
    iannopoulos
    -0.75
     behavi
    -0.73
     Afric
    -0.70
     synd
    -0.64
     Tactics
    -0.63
     Synd
    -0.61
     Pai
    -0.61
     ASC
    -0.59
     agent
    -0.59
    conservancy
    -0.58
    POSITIVE LOGITS
    į
    1.46
    ·
    1.43
    ¡
    1.42
    ¬
    1.40
    ´
    1.38
    ¼
    1.37
    ¢
    1.37
    Ń
    1.36
    £
    1.34
    Ĵ
    1.33
    Activations Density 0.115%

    No Known Activations