© 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. 16096
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entity mentions

    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
    1:0.03
    2:0.04
    3:0.07
    4:0.03
    5:0.06
    6:0.14
    7:0.04
    8:0.03
    9:0.42
    10:0.02
    11:0.02
    Negative Logits
    Tan
    -3.69
     sten
    -3.63
    STON
    -3.63
    Balt
    -3.62
    sta
    -3.60
     Tosh
    -3.54
    ston
    -3.53
     Clayton
    -3.49
     Wallace
    -3.48
    sten
    -3.42
    POSITIVE LOGITS
    iv
    5.17
     Hive
    5.09
    ive
    5.00
    ived
    4.45
    IV
    4.35
    ives
    4.09
    iver
    3.97
    IVE
    3.95
    ivation
    3.92
    iva
    3.89
    Activations Density 0.002%

    No Known Activations