© 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. 22167
    Prev
    Next
    INDEX
    Explanations

    complex actions or events involving interpersonal relationships and consequences

    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
    0:0.07
    1:0.06
    2:0.30
    3:0.07
    4:0.05
    5:0.02
    6:0.07
    7:0.07
    8:0.02
    9:0.09
    10:0.07
    11:0.05
    Negative Logits
    Guard
    -3.39
    oğ
    -3.22
    �
    -3.15
    jriwal
    -3.14
    ÍÍ
    -3.03
    )=(
    -2.99
    TPP
    -2.92
    arbon
    -2.91
     largeDownload
    -2.86
    Percent
    -2.84
    POSITIVE LOGITS
     Lydia
    5.64
     Brenda
    5.48
     Sylvia
    5.40
     Valerie
    5.35
     Melanie
    5.28
     Diane
    5.26
     Erica
    5.26
     Claudia
    5.23
     Rebecca
    5.18
     Carolyn
    5.18
    Activations Density 0.516%

    No Known Activations