© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 8445
    Prev
    Next
    INDEX
    Explanations

    sentences that end with specific non-alphabetical characters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hancock
    -0.86
     homebrew
    -0.80
     scrambling
    -0.75
     hindsight
    -0.74
     Weaver
    -0.74
     Scion
    -0.74
     Austin
    -0.73
     bourbon
    -0.73
     Wyatt
    -0.71
     Floyd
    -0.71
    POSITIVE LOGITS
    Translation
    1.12
    à¦
    1.08
    Moreover
    1.07
    ³³³³³³³³³³³³³³³³
    1.03
    Balt
    1.03
    âĵĺ
    1.02
    ë
    1.02
    ×ŀ
    1.00
    ê
    0.99
    ع
    0.99
    Activations Density 0.372%

    No Known Activations