© 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. 11-RES-JB
    11. 13498
    Prev
    Next
    INDEX
    Explanations

    contractions of the word "we are"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the phrase "we're."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \/
    -0.76
    Scroll
    -0.71
    ESE
    -0.70
    DS
    -0.70
    odder
    -0.66
    TAIN
    -0.66
    \.
    -0.64
    iola
    -0.62
    ®,
    -0.61
    ren
    -0.61
    POSITIVE LOGITS
     gonna
    1.34
     not
    1.08
     gotta
    1.04
     sorry
    0.99
     guessing
    0.96
     going
    0.94
     supposed
    0.91
     glad
    0.90
     hoping
    0.86
     afraid
    0.83
    Activations Density 0.086%

    No Known Activations