© 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. 24501
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and decisions

    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
    0:0.07
    1:0.03
    2:0.11
    3:0.13
    4:0.05
    5:0.14
    6:0.03
    7:0.11
    8:0.14
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
    Ready
    -2.76
     Millennials
    -2.57
    ®,
    -2.35
    ®
    -2.32
     AMERICA
    -2.29
    EStream
    -2.21
    NAS
    -2.14
     Races
    -2.11
    America
    -2.11
     Democr
    -2.10
    POSITIVE LOGITS
    ihar
    3.06
     Kerala
    3.01
     Delhi
    3.01
     Rs
    2.94
     Vish
    2.89
    jriwal
    2.89
     BJP
    2.87
     complainant
    2.83
     CCTV
    2.80
     Kejriwal
    2.76
    Activations Density 0.170%

    No Known Activations