© 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. 10-RES-JB
    11. 18789
    Prev
    Next
    INDEX
    Explanations

    technology-related terms such as "phones," "streams," and "contractors."

    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
    BuyableInstoreAndOnline
    -0.88
     CLS
    -0.70
    ãĤ´ãĥ³
    -0.64
    UGC
    -0.63
    ĸļ
    -0.60
     lamented
    -0.59
     Released
    -0.58
    uton
    -0.58
     famed
    -0.56
    surprisingly
    -0.55
    POSITIVE LOGITS
     [
    1.19
     everybody
    1.19
     ['
    1.16
     somebody
    1.15
     âĢ¦
    1.11
    ."
    1.10
     gonna
    1.09
    .''
    1.09
     stuff
    1.09
    ,"
    1.07
    Activations Density 1.119%

    No Known Activations