© 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. 9-ATT-KK
    11. 14610
    Prev
    Next
    INDEX
    Explanations

    content related to financial accountability and theft

    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
    1:0.02
    2:0.08
    3:0.03
    4:0.04
    5:0.04
    6:0.34
    7:0.02
    8:0.04
    9:0.22
    10:0.02
    11:0.02
    Negative Logits
    SM
    -3.77
     microw
    -3.63
     Morty
    -3.58
    MAG
    -3.56
     Malfoy
    -3.56
    cookie
    -3.56
     Yel
    -3.55
     Scha
    -3.46
     Mew
    -3.40
    Hun
    -3.33
    POSITIVE LOGITS
     bridge
    10.98
     Bridge
    10.65
     bridges
    9.82
    Bridge
    9.35
     Bridges
    8.95
    bridge
    7.73
     brid
    6.51
    brid
    4.96
     Brid
    4.61
     river
    4.22
    Activations Density 0.016%

    No Known Activations