© 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. 11662
    Prev
    Next
    INDEX
    Explanations

    references to competitive racing events and participant 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
    0:0.20
    1:0.03
    2:0.11
    3:0.10
    4:0.05
    5:0.11
    6:0.06
    7:0.05
    8:0.12
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
    usterity
    -2.95
    ibrary
    -2.84
     Chomsky
    -2.82
     Wikileaks
    -2.59
     poems
    -2.59
     cens
    -2.55
    ulhu
    -2.52
    oldemort
    -2.52
    anamo
    -2.50
     Assange
    -2.48
    POSITIVE LOGITS
     Motorsport
    4.65
     FIA
    4.06
     Racing
    3.97
     racing
    3.90
     GT
    3.87
     Formula
    3.85
     motors
    3.70
     racer
    3.67
     Porsche
    3.62
     Renault
    3.60
    Activations Density 0.128%

    No Known Activations