© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 22233
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms and concepts related to court proceedings

    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
    0:0.10
    1:0.02
    2:0.08
    3:0.24
    4:0.03
    5:0.12
    6:0.01
    7:0.07
    8:0.13
    9:0.02
    10:0.11
    11:0.02
    Negative Logits
    ®,
    -2.15
    SIGN
    -2.10
    blow
    -2.10
    ♥
    -2.03
     probabilities
    -1.95
    antz
    -1.95
     Barbie
    -1.90
    sym
    -1.87
    isSpecialOrderable
    -1.86
    ipples
    -1.86
    POSITIVE LOGITS
     Delhi
    3.59
    jriwal
    3.58
     Kejriwal
    3.31
     Gujarat
    3.27
     Lok
    3.21
     Pradesh
    3.19
     Chennai
    3.19
     Maharashtra
    3.17
     Vish
    3.15
     BJP
    3.04
    Activations Density 0.462%

    No Known Activations