© 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. 7901
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "email."

    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
    0:0.02
    1:0.01
    2:0.04
    3:0.05
    4:0.25
    5:0.07
    6:0.03
    7:0.03
    8:0.15
    9:0.23
    10:0.06
    11:0.01
    Negative Logits
     sugg
    -2.41
     imbalance
    -2.20
     plurality
    -2.09
    Origin
    -2.06
     hypers
    -2.05
     hordes
    -2.03
    cific
    -2.01
    tones
    -2.01
     embodiments
    -2.00
    uria
    -1.96
    POSITIVE LOGITS
     by
    2.63
     By
    2.30
    by
    2.29
     signing
    2.24
    usted
    2.17
    "></
    2.16
    anging
    2.15
    inning
    2.01
    By
    1.96
    gaard
    1.95
    Activations Density 0.001%

    No Known Activations