© 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. 12920
    Prev
    Next
    INDEX
    Explanations

    mentions of prominent individuals or brands in contexts related to product endorsements or performance 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
    0:0.07
    1:0.21
    2:0.04
    3:0.05
    4:0.04
    5:0.03
    6:0.18
    7:0.03
    8:0.02
    9:0.24
    10:0.02
    11:0.03
    Negative Logits
     hallucinations
    -3.24
     LU
    -3.17
    anchester
    -3.11
     halluc
    -3.03
    aughs
    -2.99
     MAT
    -2.97
    LU
    -2.94
     Peb
    -2.93
    azel
    -2.89
     Dund
    -2.87
    POSITIVE LOGITS
    TOP
    5.93
     Top
    5.84
     TOP
    5.67
    Top
    5.33
    top
    5.17
     top
    4.69
    tops
    4.63
     topping
    4.53
     tops
    4.25
     topped
    4.08
    Activations Density 0.005%

    No Known Activations