© 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. 2452
    Prev
    Next
    INDEX
    Explanations

    arguments or opinions related to controversial social issues

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

    claims about gender and racial superiority or inferiority

    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
    onductor
    -0.80
    ilde
    -0.78
     unfocusedRange
    -0.73
    ileaks
    -0.73
    ospons
    -0.72
    iHUD
    -0.71
    bernatorial
    -0.70
    kamp
    -0.69
    tains
    -0.68
    kHz
    -0.67
    POSITIVE LOGITS
     idiots
    1.21
     saints
    1.18
     rapists
    1.17
     sinners
    1.17
     interchangeable
    1.10
     murderers
    1.10
     monsters
    1.06
     racists
    1.05
     inherently
    1.04
     parasites
    1.03
    Activations Density 0.283%

    No Known Activations