© 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. 11-RES-JB
    11. 12867
    Prev
    Next
    INDEX
    Explanations

    particular verbs related to processes or methods

    oai_token-act-pair · gpt-3.5-turbo

    sentences that describe processes or methods with an emphasis on their effectiveness or issues

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     worries
    -0.73
     Awakens
    -0.70
     pockets
    -0.70
     Signs
    -0.70
     Flavoring
    -0.69
     Pavilion
    -0.66
     seats
    -0.65
    aques
    -0.63
     tears
    -0.63
     Sources
    -0.63
    POSITIVE LOGITS
     perfected
    1.16
     devised
    1.15
     pioneered
    1.12
     adapted
    1.06
     ingenious
    1.06
     simplified
    1.05
     iter
    1.02
     practiced
    1.02
     scalable
    1.01
     simpler
    1.00
    Activations Density 0.316%

    No Known Activations