© 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. 14210
    Prev
    Next
    INDEX
    Explanations

    words related to opposition or criticism, especially of a political or ideological nature

    oai_token-act-pair · gpt-3.5-turbo

    expressions of anti-ideologies related to various social and political issues

    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
    ĸļ
    -0.75
     Sins
    -0.75
     Sabha
    -0.74
     Tycoon
    -0.73
     Nights
    -0.71
     resid
    -0.70
     Known
    -0.70
     McGee
    -0.68
     Lords
    -0.67
     Gorge
    -0.64
    POSITIVE LOGITS
    abortion
    1.31
    establishment
    1.13
    war
    1.08
    immigrant
    1.03
    Semitic
    1.03
    union
    0.96
    femin
    0.96
    racist
    0.94
    aligned
    0.89
    -
    0.88
    Activations Density 0.039%

    No Known Activations