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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18928
    Prev
    Next
    INDEX
    Explanations

    statistical data related to demographics and charitable contributions

    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
    0:0.02
    1:0.03
    2:0.02
    3:0.10
    4:0.04
    5:0.07
    6:0.16
    7:0.02
    8:0.02
    9:0.09
    10:0.06
    11:0.32
    Negative Logits
     crab
    -3.02
    Advertisement
    -2.90
     —
    -2.86
    —
    -2.74
     Seraph
    -2.73
     ­
    -2.70
    Alert
    -2.62
     iceberg
    -2.54
     lobster
    -2.53
     Tup
    -2.50
    POSITIVE LOGITS
    `,
    6.55
    .",
    6.25
    !",
    6.24
    %),
    6.14
    %,
    6.08
    %).
    5.86
    `.
    5.56
    %.
    5.35
     ',
    5.29
    \",
    5.11
    Activations Density 0.010%

    No Known Activations