© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14312
    Prev
    Next
    INDEX
    Explanations

    connections or relationships involving multiple entities or conditions

    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
    0:0.15
    1:0.08
    2:0.04
    3:0.05
    4:0.07
    5:0.02
    6:0.09
    7:0.19
    8:0.02
    9:0.04
    10:0.11
    11:0.11
    Negative Logits
     Monument
    -2.65
    ffiti
    -2.38
     KP
    -2.28
    �
    -2.25
     Occupy
    -2.24
    �
    -2.23
    シャ
    -2.19
     Fortress
    -2.19
     Zeit
    -2.18
    代
    -2.17
    POSITIVE LOGITS
     incest
    5.02
     sperm
    3.50
     heterosexual
    3.08
     maternal
    2.88
     pregnancy
    2.87
     paternity
    2.85
     pregnancies
    2.84
     paternal
    2.83
     pedoph
    2.83
     familial
    2.72
    Activations Density 0.000%

    No Known Activations