© 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. 9-RES-JB
    11. 24322
    Prev
    Next
    INDEX
    Explanations

    instances of verbs related to accepting or refusing something

    oai_token-act-pair · gpt-3.5-turbo

    mentions of acceptance or related formal acknowledgments

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    abouts
    -0.76
     mills
    -0.71
     Alley
    -0.68
     departments
    -0.67
    acco
    -0.66
     glands
    -0.64
    ggles
    -0.62
    gallery
    -0.62
    fox
    -0.60
    lling
    -0.58
    POSITIVE LOGITS
     invitation
    1.26
     invitations
    1.01
     apology
    0.95
     responsibility
    0.91
     offer
    0.90
     resignation
    0.89
     legitimacy
    0.85
     premise
    0.84
     proposal
    0.82
     uncond
    0.82
    Activations Density 0.197%

    No Known Activations