© 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. 15850
    Prev
    Next
    INDEX
    Explanations

    phrases related to language translation and linguistic structures

    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
    0:0.10
    1:0.27
    2:0.05
    3:0.04
    4:0.04
    5:0.02
    6:0.06
    7:0.07
    8:0.02
    9:0.04
    10:0.18
    11:0.04
    Negative Logits
    pter
    -2.96
     sidel
    -2.72
    rade
    -2.71
    ノ
    -2.65
    kaya
    -2.60
    nder
    -2.60
    zzle
    -2.58
     "$:/
    -2.55
    liction
    -2.53
    Golden
    -2.51
    POSITIVE LOGITS
     Hom
    8.81
    Hom
    8.03
     hom
    7.98
    hom
    6.97
     heter
    5.90
     homophobia
    3.99
    heter
    3.91
     Hier
    3.67
     homophobic
    3.58
     homosexuality
    3.54
    Activations Density 0.017%

    No Known Activations