© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 17031
    Prev
    Next
    INDEX
    Explanations

    various key issues and themes in societal discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.18
    2:0.04
    3:0.04
    4:0.05
    5:0.03
    6:0.17
    7:0.02
    8:0.02
    9:0.27
    10:0.04
    11:0.02
    Negative Logits
     Tol
    -3.29
     Cour
    -3.28
     Ly
    -3.10
     bil
    -3.06
     Vil
    -2.99
    omers
    -2.93
     Thib
    -2.86
     Lie
    -2.83
     sworn
    -2.79
     binge
    -2.72
    POSITIVE LOGITS
    Issue
    5.52
    issue
    5.37
     issue
    4.95
     Issue
    4.87
    issues
    4.81
     issues
    4.58
    Iss
    4.58
     Issues
    4.53
    issued
    3.60
    topic
    3.56
    Activations Density 0.006%

    No Known Activations