© 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. 9-RES-JB
    11. 11414
    Prev
    Next
    INDEX
    Explanations

    numbers indicating measurements or figures

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicative of transformation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INTON
    -0.64
    wikipedia
    -0.60
    Synopsis
    -0.60
    models
    -0.59
    chapter
    -0.57
    FactoryReloaded
    -0.56
    ebook
    -0.56
    python
    -0.56
    oplan
    -0.55
    lished
    -0.55
    POSITIVE LOGITS
     scrut
    0.51
     Crusher
    0.49
     Jagu
    0.48
     Row
    0.47
     reluct
    0.46
     ster
    0.46
     Vaugh
    0.45
     Kear
    0.45
     resil
    0.44
     balk
    0.44
    Activations Density 1.709%

    No Known Activations