© 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. 8443
    Prev
    Next
    INDEX
    Explanations

    references to architectural firms and their designs

    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
    0:0.26
    1:0.02
    2:0.20
    3:0.08
    4:0.03
    5:0.07
    6:0.06
    7:0.04
    8:0.09
    9:0.05
    10:0.03
    11:0.02
    Negative Logits
     vape
    -3.29
     juice
    -3.26
     candy
    -3.12
     cig
    -3.06
     Juice
    -3.01
     vaping
    -3.00
     Wrestling
    -2.99
     Twitch
    -2.97
     stim
    -2.93
     twitch
    -2.91
    POSITIVE LOGITS
     architects
    5.91
     architect
    5.61
    itect
    5.59
     Architecture
    5.58
     architectural
    5.30
     Architects
    5.21
     Architect
    4.96
     architecture
    4.65
     Buildings
    3.95
     roofs
    3.62
    Activations Density 0.021%

    No Known Activations