© 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. 5098
    Prev
    Next
    INDEX
    Explanations

    references to interactions between countries and economic activities

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

    discussions related to social media dynamics and their impact on user interactions

    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
    abilia
    -0.62
    estern
    -0.60
    MpServer
    -0.56
    aneous
    -0.55
     himself
    -0.51
    body
    -0.51
    abre
    -0.50
    appropriate
    -0.50
    omore
    -0.50
    isations
    -0.50
    POSITIVE LOGITS
     Its
    1.20
    Its
    1.12
     its
    1.02
     ITS
    0.78
     boasts
    0.76
     operates
    0.76
     relies
    0.74
    its
    0.73
     lacks
    0.72
     employs
    0.72
    Activations Density 0.790%

    No Known Activations