© 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. 19435
    Prev
    Next
    INDEX
    Explanations

    references to specific car models and their details

    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
    0:0.17
    1:0.02
    2:0.06
    3:0.06
    4:0.05
    5:0.04
    6:0.13
    7:0.06
    8:0.15
    9:0.12
    10:0.03
    11:0.05
    Negative Logits
     Dice
    -3.60
    cean
    -3.13
     lawy
    -3.05
     salsa
    -2.98
     dice
    -2.97
     Brow
    -2.96
     Lann
    -2.89
     Cuban
    -2.84
     Guant
    -2.84
    cells
    -2.83
    POSITIVE LOGITS
     Subaru
    9.68
    aru
    4.61
     Suzuki
    4.49
     Toyota
    4.46
     Nissan
    4.36
     Honda
    4.31
     Scion
    3.95
     Mits
    3.93
     Volkswagen
    3.86
     Fuji
    3.75
    Activations Density 0.001%

    No Known Activations