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

    Neuronpedia

    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. 440
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names in the text

    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
    1:0.01
    2:0.02
    3:0.10
    4:0.03
    5:0.13
    6:0.03
    7:0.21
    8:0.04
    9:0.02
    10:0.28
    11:0.02
    Negative Logits
     exhilar
    -2.00
    years
    -2.00
     photograp
    -1.97
     exclaim
    -1.97
     triumph
    -1.95
     irresist
    -1.93
     danced
    -1.92
     comparing
    -1.90
     colours
    -1.87
     fun
    -1.82
    POSITIVE LOGITS
    het
    2.20
    inar
    2.19
    chel
    2.11
    pton
    2.08
    rahim
    2.07
    essen
    2.06
    tails
    2.02
    stress
    1.97
    chell
    1.96
    oppy
    1.94
    Activations Density 0.003%

    No Known Activations