© 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. 12-RES-JB
    11. 2409
    Prev
    Next
    INDEX
    Explanations

    words related to relationships and connections between people

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    the conjunction "and" used 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 @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    VEN
    -0.70
    RESULTS
    -0.61
    undle
    -0.60
    ç·
    -0.58
    answered
    -0.58
    is
    -0.58
    itionally
    -0.57
    HY
    -0.57
     Dealer
    -0.57
    èĢħ
    -0.56
    POSITIVE LOGITS
     breathing
    1.01
     limb
    0.99
     breat
    0.92
     death
    0.91
     breathe
    0.90
     breathed
    0.87
     liberty
    0.84
     dying
    0.82
     work
    0.82
    death
    0.81
    Activations Density 0.132%

    No Known Activations