© 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. 21917
    Prev
    Next
    INDEX
    Explanations

    references to products and services associated with The New York Times

    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
    0:0.19
    1:0.03
    2:0.04
    3:0.11
    4:0.11
    5:0.13
    6:0.04
    7:0.07
    8:0.03
    9:0.02
    10:0.17
    11:0.01
    Negative Logits
     posters
    -2.31
    iple
    -2.16
    ㅋㅋ
    -2.07
     congrat
    -2.05
     obser
    -2.05
     marqu
    -2.00
    uminati
    -2.00
     Actress
    -1.97
     Fifa
    -1.95
     signage
    -1.94
    POSITIVE LOGITS
     Travels
    2.10
    icht
    2.07
    dL
    2.00
    omas
    1.96
    inations
    1.90
    Volume
    1.89
    itus
    1.88
    osis
    1.87
    ridges
    1.83
    FFER
    1.83
    Activations Density 0.005%

    No Known Activations