© 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. 14248
    Prev
    Next
    INDEX
    Explanations

    references to different political parties and their involvement in decision-making

    oai_token-act-pair · gpt-3.5-turbo

    references to political party affiliations and diversity

    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
    ovember
    -0.84
    uilding
    -0.80
     staging
    -0.79
     haunt
    -0.78
     disposal
    -0.74
     rehe
    -0.74
     forecasting
    -0.73
     booking
    -0.73
     assay
    -0.73
     rapp
    -0.71
    POSITIVE LOGITS
     Croat
    1.14
     Elven
    0.98
     Veget
    0.97
     Protoss
    0.96
     Protestants
    0.92
     Protestant
    0.92
     Scandinavian
    0.91
     Orthodox
    0.90
     Anarch
    0.89
     Reds
    0.88
    Activations Density 0.313%

    No Known Activations