© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 10323
    Prev
    Next
    INDEX
    Explanations

    statements involving personal interactions and public relations, particularly in the context of legal and media scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.22
    1:0.09
    2:0.10
    3:0.03
    4:0.02
    5:0.02
    6:0.09
    7:0.16
    8:0.01
    9:0.04
    10:0.11
    11:0.04
    Negative Logits
     Emir
    -3.55
     UAE
    -3.09
     Neb
    -2.89
    Sphere
    -2.80
     Rub
    -2.80
     Aer
    -2.78
     Farn
    -2.76
     maid
    -2.76
     haz
    -2.72
     spark
    -2.70
    POSITIVE LOGITS
     Thompson
    7.92
    Thompson
    7.86
     Thom
    3.64
    Golden
    3.46
     Warriors
    3.43
     Kerr
    3.27
     Golden
    3.16
     Curry
    3.15
     Parker
    3.14
     Montana
    3.14
    Activations Density 0.011%

    No Known Activations