© 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. 11-RES-JB
    11. 12892
    Prev
    Next
    INDEX
    Explanations

    words related to political actions, such as "abstained," "impeached," and "inaugurated."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political processes and actions, especially regarding abstaining and impeachment

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     econom
    -0.76
     Frey
    -0.73
     surrog
    -0.72
     pecul
    -0.71
     behavi
    -0.70
     asymm
    -0.69
    manship
    -0.67
     similarities
    -0.67
    INESS
    -0.66
     factors
    -0.66
    POSITIVE LOGITS
    uted
    1.33
    ained
    1.18
    ended
    1.16
    ached
    1.15
    urated
    1.08
    aining
    1.05
    osed
    1.03
    azed
    1.02
    icted
    1.02
    uled
    1.01
    Activations Density 0.084%

    No Known Activations