© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 305
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, particularly states and universities

    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
    0:0.05
    1:0.03
    2:0.03
    3:0.08
    4:0.04
    5:0.09
    6:0.15
    7:0.04
    8:0.05
    9:0.32
    10:0.05
    11:0.02
    Negative Logits
     Alph
    -3.76
     marqu
    -3.31
    eng
    -3.21
     Levy
    -3.17
     Kens
    -3.02
    jp
    -2.97
     Caf
    -2.96
     Scorp
    -2.96
     influ
    -2.95
    DJ
    -2.92
    POSITIVE LOGITS
     STATE
    3.89
     State
    3.71
     Simone
    3.64
    ummer
    3.31
     Tao
    3.30
    STATE
    3.28
     Samoa
    3.22
     sage
    3.20
    SM
    3.19
    uman
    3.16
    Activations Density 0.003%

    No Known Activations