© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 5094
    Prev
    Next
    INDEX
    Explanations

    the word "op"

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    terms associated with ranking or position

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ACTIONS
    -0.69
    é¾įå¥ij士
    -0.62
    artifacts
    -0.62
     Pact
    -0.61
    %%%%
    -0.58
    pled
    -0.58
     pact
    -0.57
    lication
    -0.56
     cellul
    -0.56
     analges
    -0.56
    POSITIVE LOGITS
    rette
    0.93
    arde
    0.89
    isite
    0.87
    onne
    0.81
    ard
    0.80
    minster
    0.77
    orce
    0.76
    ousse
    0.75
    itsch
    0.75
    oux
    0.74
    Activations Density 0.141%

    No Known Activations