© 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. 13823
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and connectors in text

    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
    0:0.07
    1:0.05
    2:0.07
    3:0.03
    4:0.07
    5:0.04
    6:0.21
    7:0.05
    8:0.06
    9:0.23
    10:0.03
    11:0.03
    Negative Logits
    sequence
    -3.77
     Jae
    -3.71
     Jensen
    -3.68
    hal
    -3.44
     Hansen
    -3.43
     Magnus
    -3.29
    gaard
    -3.24
    rolog
    -3.13
    lock
    -3.09
    jin
    -3.08
    POSITIVE LOGITS
     Betty
    10.33
    Bet
    7.28
     Bet
    5.71
     Archie
    5.41
    bet
    4.72
     Byrd
    4.37
     Butter
    4.31
     BET
    4.28
     Bert
    4.20
    Cow
    4.15
    Activations Density 0.001%

    No Known Activations