© 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. 10-ATT-KK
    11. 14449
    Prev
    Next
    INDEX
    Explanations

    economic data and trends

    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
    0:0.02
    1:0.01
    2:0.03
    3:0.30
    4:0.37
    5:0.10
    6:0.01
    7:0.02
    8:0.01
    9:0.04
    10:0.01
    11:0.02
    Negative Logits
    \",
    -3.81
    "},
    -3.73
    `,
    -3.63
    ",
    -3.50
    ","
    -3.49
    "],
    -3.42
    ":{"
    -3.18
    ``
    -2.97
    \":
    -2.93
    `
    -2.80
    POSITIVE LOGITS
    .)
    7.31
    .)
    7.25
    .")
    7.09
    !)
    4.97
    …)
    4.89
    .):
    4.79
    .).
    4.79
    ?)
    4.77
    )."
    4.64
    ...)
    4.22
    Activations Density 0.056%

    No Known Activations