© 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. 2348
    Prev
    Next
    INDEX
    Explanations

    contractions and possessive forms of words

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

    contractions and negations in the text

    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
    udos
    -0.64
     Flavoring
    -0.62
     desires
    -0.57
    âĵĺ
    -0.57
     endeavors
    -0.57
    ulkan
    -0.57
    eter
    -0.57
     Conversely
    -0.56
    ples
    -0.56
    find
    -0.55
    POSITIVE LOGITS
     raining
    1.10
     gonna
    0.97
     happening
    0.88
     okay
    0.84
     funny
    0.83
     bullshit
    0.81
     alright
    0.79
     hilarious
    0.74
     ok
    0.74
     disgusting
    0.72
    Activations Density 0.352%

    No Known Activations