© 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. 12677
    Prev
    Next
    INDEX
    Explanations

    inquiries regarding societal norms and questions surrounding personal relationships and family dynamics

    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
    0:0.03
    1:0.03
    2:0.02
    3:0.03
    4:0.16
    5:0.25
    6:0.03
    7:0.08
    8:0.02
    9:0.21
    10:0.02
    11:0.06
    Negative Logits
    KO
    -2.35
    opp
    -2.27
    orks
    -2.23
    respect
    -2.13
    ffect
    -2.08
     Coord
    -2.05
     Donation
    -2.04
     fucked
    -1.99
     SetFontSize
    -1.96
     Illusion
    -1.95
    POSITIVE LOGITS
     unanswered
    3.47
    Answer
    3.34
    answer
    3.29
     answer
    3.19
    answered
    3.10
     answered
    2.80
     answers
    2.78
     Flavoring
    2.74
    undrum
    2.73
    :{
    2.71
    Activations Density 0.094%

    No Known Activations