© 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. 14114
    Prev
    Next
    INDEX
    Explanations

    terminology related to laws, regulations, and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to international relations and government policies

    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
     teammates
    -0.74
     teammate
    -0.71
     testers
    -0.70
     slot
    -0.67
     elbow
    -0.66
     workaround
    -0.66
     brass
    -0.65
     penalty
    -0.64
     discretion
    -0.64
     stash
    -0.64
    POSITIVE LOGITS
    Economic
    0.93
     Its
    0.92
    terrorism
    0.91
    Econom
    0.83
    democracy
    0.83
    national
    0.79
     Capitalism
    0.79
    global
    0.79
    ;;;;;;;;;;;;
    0.78
     Agenda
    0.76
    Activations Density 0.656%

    No Known Activations