© 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. 15622
    Prev
    Next
    INDEX
    Explanations

    pronouns and terms indicating participation or involvement

    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
    0:0.10
    1:0.08
    2:0.07
    3:0.22
    4:0.04
    5:0.06
    6:0.02
    7:0.07
    8:0.06
    9:0.02
    10:0.18
    11:0.04
    Negative Logits
     whom
    -2.19
    imon
    -2.14
    appointed
    -2.03
     Bagg
    -2.02
    etermined
    -2.00
    Sem
    -1.98
    catentry
    -1.96
    imony
    -1.91
    grave
    -1.86
     Hazard
    -1.84
    POSITIVE LOGITS
     shit
    2.71
     crap
    2.39
     fucked
    2.37
     smarter
    2.30
     WAY
    2.26
     shortcuts
    2.25
     backdoor
    2.22
     poop
    2.19
     fuck
    2.10
     piss
    2.10
    Activations Density 0.001%

    No Known Activations