© 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. 7-RES-JB
    11. 9538
    Prev
    Next
    INDEX
    Explanations

    contractions that include "are" followed by an adjective

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the contraction "we're."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reduce
    -0.72
     mater
    -0.70
    ESE
    -0.69
    andise
    -0.68
     membr
    -0.63
    TAIN
    -0.62
    ={
    -0.61
    iates
    -0.60
    DS
    -0.60
    acters
    -0.59
    POSITIVE LOGITS
     gonna
    1.45
     gotta
    1.13
     hoping
    1.01
     going
    0.99
     supposed
    0.95
     guessing
    0.92
     afraid
    0.92
     glad
    0.91
     got
    0.90
     sorry
    0.88
    Activations Density 0.068%

    No Known Activations