© 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. 12990
    Prev
    Next
    INDEX
    Explanations

    multiple occurrences of the word "and" in relation to various topics, indicating a focus on connections and relationships

    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
    0:0.04
    1:0.03
    2:0.03
    3:0.04
    4:0.11
    5:0.02
    6:0.03
    7:0.44
    8:0.02
    9:0.04
    10:0.03
    11:0.11
    Negative Logits
     Land
    -3.73
    Land
    -3.44
     Lands
    -3.25
     Weed
    -2.98
    land
    -2.79
     Hannah
    -2.74
     landowners
    -2.73
     Krypt
    -2.62
    Lex
    -2.62
    lands
    -2.61
    POSITIVE LOGITS
     Rodrigo
    2.93
    olphins
    2.75
     Jian
    2.52
     Rubio
    2.52
    ucci
    2.50
    rob
    2.46
     resc
    2.44
    oji
    2.42
    IRO
    2.41
    rw
    2.40
    Activations Density 0.027%

    No Known Activations