© 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. 9-ATT-KK
    11. 20472
    Prev
    Next
    INDEX
    Explanations

    references to significant societal issues or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.02
    2:0.04
    3:0.09
    4:0.16
    5:0.12
    6:0.12
    7:0.05
    8:0.07
    9:0.08
    10:0.03
    11:0.04
    Negative Logits
    Denver
    -2.79
    thouse
    -2.67
    olitan
    -2.65
    Detroit
    -2.61
    Seattle
    -2.59
    rican
    -2.49
    lando
    -2.42
    Atlanta
    -2.42
    archy
    -2.38
    orney
    -2.37
    POSITIVE LOGITS
     Cum
    2.89
     Pog
    2.76
     Ort
    2.70
     Lak
    2.69
     Kas
    2.68
     Coch
    2.66
     Kor
    2.63
     Kol
    2.63
     Chat
    2.63
     Ack
    2.60
    Activations Density 0.226%

    No Known Activations