© 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. 17668
    Prev
    Next
    INDEX
    Explanations

    references to literature or classical works

    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
    0:0.19
    1:0.01
    2:0.15
    3:0.06
    4:0.02
    5:0.10
    6:0.07
    7:0.05
    8:0.19
    9:0.08
    10:0.03
    11:0.01
    Negative Logits
     Zoro
    -3.99
     mt
    -3.84
     Yug
    -3.53
     healed
    -3.30
     Sapphire
    -3.25
     Miner
    -3.24
     Mineral
    -3.21
    ammad
    -3.07
     Mesa
    -3.02
     Grave
    -3.02
    POSITIVE LOGITS
     Orwell
    7.96
     dystopian
    4.97
     totalitarian
    4.79
     dystop
    4.65
     Snowden
    3.52
    CHQ
    3.50
    Privacy
    3.49
     leaflets
    3.46
     authoritarian
    3.45
     censorship
    3.44
    Activations Density 0.001%

    No Known Activations