© 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. 8-RES-JB
    11. 13141
    Prev
    Next
    INDEX
    Explanations

    imperative sentences starting with "You'll be" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "be" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    osate
    -0.72
    strous
    -0.72
    olitics
    -0.67
     relativity
    -0.66
     Stability
    -0.65
     dispel
    -0.62
     falsehood
    -0.62
     disorder
    -0.62
     reconstruction
    -0.62
     mandate
    -0.62
    POSITIVE LOGITS
     able
    1.43
     glad
    1.21
     amazed
    1.15
     thankful
    1.11
     surprised
    1.10
     grateful
    1.07
     pleased
    1.05
     tempted
    1.01
     thrilled
    1.00
     happy
    0.99
    Activations Density 0.136%

    No Known Activations