© 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. 2456
    Prev
    Next
    INDEX
    Explanations

    content related to politics and economics

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

    references to economic impacts and financial figures

    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
     Attribution
    -0.91
    lique
    -0.75
    Appearance
    -0.75
    oward
    -0.73
    igmatic
    -0.73
    canon
    -0.73
     Dating
    -0.72
    é¾įåĸļ士
    -0.72
     practition
    -0.70
    onomy
    -0.70
    POSITIVE LOGITS
     impover
    1.29
     trillions
    1.20
     unemploy
    1.20
     privat
    1.11
     wasteful
    1.09
     bankrupt
    1.07
     subsid
    1.07
     poorer
    1.06
     billions
    1.06
     poverty
    1.06
    Activations Density 0.995%

    No Known Activations