© 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. 528
    Prev
    Next
    INDEX
    Explanations

    phrases related to business partnerships and supply agreements

    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
    0:0.11
    1:0.02
    2:0.10
    3:0.05
    4:0.07
    5:0.06
    6:0.16
    7:0.05
    8:0.11
    9:0.14
    10:0.04
    11:0.04
    Negative Logits
     Rowe
    -4.01
     sock
    -3.46
    nder
    -3.43
    ��
    -3.13
     Byrd
    -3.08
     Roose
    -3.04
     Dread
    -2.97
    estinal
    -2.96
     graves
    -2.96
    Aust
    -2.93
    POSITIVE LOGITS
     Panasonic
    9.52
    Pan
    5.25
     Kod
    4.49
     Olympus
    4.31
     Fuji
    4.21
    panel
    4.06
     Nikon
    3.93
     OEM
    3.93
     Philips
    3.90
     Canon
    3.80
    Activations Density 0.002%

    No Known Activations