© 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. 23860
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and other grammatical elements that provide structure to sentences

    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
    0:0.13
    1:0.03
    2:0.04
    3:0.06
    4:0.06
    5:0.06
    6:0.17
    7:0.03
    8:0.05
    9:0.26
    10:0.04
    11:0.02
    Negative Logits
     Kirin
    -3.97
    nav
    -3.71
     Paladin
    -3.57
    ��
    -3.44
    NS
    -3.33
    hover
    -3.32
     Regist
    -3.26
    valid
    -3.20
     Obj
    -3.17
    pring
    -3.15
    POSITIVE LOGITS
     tapes
    8.65
     tape
    8.02
     Tape
    8.01
     taped
    6.46
     cassette
    5.60
     cass
    4.85
     videot
    4.15
     clips
    4.08
    ape
    4.02
     CDs
    3.96
    Activations Density 0.002%

    No Known Activations