© 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. 3-RES-JB
    11. 16701
    Prev
    Next
    INDEX
    Explanations

    words related to software and technology, specifically focusing on various software applications or tools

    oai_token-act-pair · gpt-3.5-turbo

    specific software names or terms related to technology

    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
     saturated
    -0.67
     decaying
    -0.65
     declining
    -0.63
     dwindling
    -0.60
     stabilized
    -0.58
     converted
    -0.58
     fractured
    -0.58
    ĨĴ
    -0.57
     melted
    -0.57
     deteriorating
    -0.57
    POSITIVE LOGITS
    ById
    0.66
    luster
    0.65
    neau
    0.64
    tons
    0.64
    ãĤª
    0.64
    advertising
    0.64
     Travels
    0.63
    ãĤ¼
    0.63
    Factory
    0.63
    Pg
    0.63
    Activations Density 0.821%

    No Known Activations