© 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. 10-ATT-KK
    11. 8917
    Prev
    Next
    INDEX
    Explanations

    various occurrences and forms of the word "the" or related articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.15
    2:0.26
    3:0.07
    4:0.03
    5:0.02
    6:0.03
    7:0.20
    8:0.03
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
    Deal
    -2.66
    3000
    -2.53
    CHAR
    -2.43
     Link
    -2.37
    RA
    -2.33
     Tags
    -2.30
    DEF
    -2.29
     Committees
    -2.27
    Sync
    -2.27
    HE
    -2.25
    POSITIVE LOGITS
     eighth
    4.94
     ninth
    4.79
     seventh
    4.71
     sixth
    4.54
     tenth
    4.49
     Ninth
    4.46
     fifth
    4.39
     Sixth
    4.39
     Eighth
    4.37
     Fifth
    4.04
    Activations Density 0.017%

    No Known Activations