© 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. 16474
    Prev
    Next
    INDEX
    Explanations

    instances of the word "enter."

    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
    0:0.19
    1:0.04
    2:0.05
    3:0.09
    4:0.06
    5:0.04
    6:0.06
    7:0.17
    8:0.03
    9:0.06
    10:0.12
    11:0.04
    Negative Logits
    Dutch
    -2.71
     Claus
    -2.65
     Calais
    -2.58
    anon
    -2.54
     Danish
    -2.48
    ◼
    -2.46
    Ire
    -2.45
     Flames
    -2.44
     gravy
    -2.43
     Fas
    -2.38
    POSITIVE LOGITS
    xual
    3.18
    ozo
    2.88
     Spart
    2.88
     Socrates
    2.85
     Zan
    2.69
    ury
    2.69
     laure
    2.63
     Plato
    2.57
     UA
    2.51
    inct
    2.50
    Activations Density 0.000%

    No Known Activations