© 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. 18718
    Prev
    Next
    INDEX
    Explanations

    mentions of different editions of books, products, and publications

    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
    yah
    -0.64
    amera
    -0.63
    uli
    -0.62
    eating
    -0.62
    eric
    -0.60
    yp
    -0.59
    amen
    -0.59
     procedural
    -0.59
    animate
    -0.59
     decl
    -0.58
    POSITIVE LOGITS
     edition
    0.89
     thereof
    0.86
     editions
    0.80
     EDITION
    0.76
     Edition
    0.75
    velop
    0.74
    edition
    0.72
     of
    0.70
    ansion
    0.68
    ctl
    0.67
    Activations Density 0.047%

    No Known Activations