© 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. 17867
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to long-term and short-term considerations or effects

    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
    0:0.06
    1:0.11
    2:0.08
    3:0.05
    4:0.04
    5:0.04
    6:0.14
    7:0.04
    8:0.04
    9:0.28
    10:0.03
    11:0.03
    Negative Logits
     Lak
    -3.47
     Lana
    -3.22
     Citiz
    -3.11
    jit
    -3.10
    ipel
    -3.09
     Cout
    -3.08
    Luck
    -3.08
     Kelly
    -3.05
     TRUMP
    -3.02
     OCD
    -3.01
    POSITIVE LOGITS
    Term
    7.02
     Term
    6.76
    term
    5.82
     term
    5.80
    terms
    4.04
    Graph
    3.98
     membrane
    3.70
    rums
    3.66
     membranes
    3.63
    agar
    3.61
    Activations Density 0.002%

    No Known Activations