© 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. 7-RES-JB
    11. 24096
    Prev
    Next
    INDEX
    Explanations

    programming commands related to Android development

    oai_token-act-pair · gpt-3.5-turbo

    negative indicators or issues related to Android development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Norris
    -0.76
     Yaz
    -0.75
     Vaughan
    -0.71
     Hanson
    -0.71
     Gunn
    -0.70
     Lowry
    -0.69
     Phelps
    -0.69
     Cassidy
    -0.69
     Emmy
    -0.69
     Jasper
    -0.69
    POSITIVE LOGITS
    mode
    1.17
    sama
    1.11
    notation
    1.11
    generic
    1.09
    wrapper
    1.08
    utils
    1.07
    type
    1.06
    setup
    1.06
    server
    1.05
    package
    1.04
    Activations Density 0.134%

    No Known Activations