© 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. 11112
    Prev
    Next
    INDEX
    Explanations

    sentences with references to motorcycle racing events and teams

    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
    0:0.12
    1:0.02
    2:0.07
    3:0.05
    4:0.04
    5:0.04
    6:0.19
    7:0.06
    8:0.16
    9:0.16
    10:0.02
    11:0.03
    Negative Logits
     Fitz
    -4.26
     blasp
    -3.75
     tox
    -3.62
     Byzantine
    -3.55
     obs
    -3.49
     plaster
    -3.46
     Wester
    -3.44
     blasphemy
    -3.43
     Kil
    -3.42
     flock
    -3.41
    POSITIVE LOGITS
     Honda
    11.43
     Suzuki
    6.91
     Yamaha
    6.72
     Hond
    6.38
     Kaw
    5.91
     Nissan
    5.51
     Moto
    5.46
     Toyota
    5.33
     Hiro
    5.27
     Harley
    5.14
    Activations Density 0.006%

    No Known Activations