© 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. 3477
    Prev
    Next
    INDEX
    Explanations

    references to classic automobiles and their attributes

    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
    0:0.15
    1:0.02
    2:0.15
    3:0.10
    4:0.09
    5:0.10
    6:0.07
    7:0.08
    8:0.08
    9:0.05
    10:0.03
    11:0.03
    Negative Logits
     caut
    -2.80
     iod
    -2.53
    monitor
    -2.47
    tile
    -2.20
    umbledore
    -2.20
    blocking
    -2.12
     infection
    -2.11
     infections
    -2.10
    iotics
    -2.09
    heter
    -2.09
    POSITIVE LOGITS
     Cadillac
    3.72
     Mustang
    3.46
     Chrysler
    3.40
     Corvette
    3.37
     Chevrolet
    3.32
     Porsche
    3.26
     Honda
    3.26
     Jeep
    3.17
     Yamaha
    3.16
     Jaguar
    3.08
    Activations Density 0.445%

    No Known Activations