© 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. 14113
    Prev
    Next
    INDEX
    Explanations

    questions starting with the word "Who"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "who" indicating questions or inquiries about identity and responsibility

    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
     Pilgrim
    -0.68
    PORT
    -0.65
    MER
    -0.63
     saturation
    -0.62
     immersion
    -0.62
     BST
    -0.61
    York
    -0.60
     Habit
    -0.60
    emin
    -0.59
     guiActiveUnfocused
    -0.59
    POSITIVE LOGITS
    soever
    1.14
    ever
    1.12
     cares
    1.10
    oping
    1.06
     else
    1.01
     knows
    0.98
    abouts
    0.90
    oped
    0.89
    ops
    0.86
     cared
    0.84
    Activations Density 0.031%

    No Known Activations