© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 5772
    Prev
    Next
    INDEX
    Explanations

    events related to political actions and meetings

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.09
    3:0.28
    4:0.05
    5:0.16
    6:0.02
    7:0.07
    8:0.06
    9:0.02
    10:0.07
    11:0.03
    Negative Logits
    "—
    -2.36
    —"
    -2.20
    "?
    -2.05
     utterly
    -1.99
     habitual
    -1.95
    "…
    -1.91
    —-
    -1.86
     clich
    -1.76
     nause
    -1.74
    )?
    -1.74
    POSITIVE LOGITS
     Statue
    2.13
     Carrier
    1.92
     USS
    1.87
    ASHINGTON
    1.82
     Sail
    1.81
     Gay
    1.79
     FILE
    1.78
    FILE
    1.73
     Donald
    1.72
     Victory
    1.72
    Activations Density 0.377%

    No Known Activations