© 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. 10231
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to investigations or inquiries related to political or legal matters

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     ç¥ŀ
    -0.86
    cil
    -0.81
    ãĤª
    -0.76
    TA
    -0.76
    keys
    -0.76
    ãĥĦ
    -0.73
    utch
    -0.72
    anguage
    -0.72
    joice
    -0.70
    alli
    -0.69
    POSITIVE LOGITS
     allegations
    1.29
     whether
    1.23
     alleged
    1.08
     misconduct
    1.08
     irregularities
    1.04
     wrongdoing
    1.02
     corruption
    1.00
     allegation
    0.96
     UFOs
    0.94
     possible
    0.93
    Activations Density 0.142%

    No Known Activations