© 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. 11000
    Prev
    Next
    INDEX
    Explanations

    categories and classifications related to living organisms

    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
    0:0.02
    1:0.05
    2:0.02
    3:0.06
    4:0.08
    5:0.45
    6:0.02
    7:0.07
    8:0.04
    9:0.02
    10:0.03
    11:0.09
    Negative Logits
     surn
    -3.42
     surname
    -3.17
     Preferred
    -3.15
     Reserv
    -3.15
     Lone
    -2.99
     Disciple
    -2.92
     designation
    -2.86
     Resident
    -2.85
     Celebrity
    -2.85
     Warrant
    -2.82
    POSITIVE LOGITS
     crib
    3.01
    azo
    2.96
    Grab
    2.83
    oros
    2.69
    paren
    2.62
    ilib
    2.60
    escal
    2.55
    ���
    2.54
    CLOSE
    2.54
     brink
    2.51
    Activations Density 0.064%

    No Known Activations