© 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. 15376
    Prev
    Next
    INDEX
    Explanations

    references to bicycle safety and infrastructure issues

    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
    0:0.13
    1:0.01
    2:0.32
    3:0.11
    4:0.02
    5:0.10
    6:0.05
    7:0.07
    8:0.07
    9:0.02
    10:0.03
    11:0.02
    Negative Logits
     Warfare
    -3.01
    ionage
    -2.92
    CIA
    -2.88
     blackmail
    -2.85
     prophe
    -2.83
     Alger
    -2.79
    agents
    -2.75
     Illuminati
    -2.67
     interrogated
    -2.67
     Cipher
    -2.66
    POSITIVE LOGITS
     biking
    6.02
     bicycl
    5.94
     cyclists
    5.91
     bicy
    5.89
     bicycle
    5.48
     bike
    5.40
     bicycles
    5.40
     cyclist
    5.38
     bikes
    5.30
     Bike
    5.24
    Activations Density 0.340%

    No Known Activations