© 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. 9-RES-JB
    11. 10284
    Prev
    Next
    INDEX
    Explanations

    phrases related to being on a particular side or position in a conflict or debate

    oai_token-act-pair · gpt-3.5-turbo

    references to opposing sides in a conflict or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESCO
    -0.85
    yrinth
    -0.74
    endi
    -0.74
    itative
    -0.72
    Ĥİ
    -0.69
    erion
    -0.68
    icut
    -0.68
    rss
    -0.65
    aila
    -0.64
    ãģ®éŃĶ
    -0.63
    POSITIVE LOGITS
    kick
    1.10
    burn
    0.93
     thereof
    0.86
    board
    0.85
    bars
    0.81
    boards
    0.81
     of
    0.78
    side
    0.77
    nee
    0.76
    real
    0.72
    Activations Density 0.034%

    No Known Activations