© 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. 10724
    Prev
    Next
    INDEX
    Explanations

    names of people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    certain names and terms related to leadership or authority figures

    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
     Dise
    -0.66
    ement
    -0.64
     inval
    -0.63
     Seraph
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.60
     Helpful
    -0.60
    ãĥ¼ãĥĨ
    -0.59
    riott
    -0.56
    soever
    -0.54
     Gleaming
    -0.54
    POSITIVE LOGITS
    yz
    0.71
    ĵĺ
    0.66
    alid
    0.63
    uild
    0.61
    ensibly
    0.59
    orb
    0.56
    ovsky
    0.56
    masters
    0.56
    hid
    0.54
    λ
    0.54
    Activations Density 0.306%

    No Known Activations