© 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 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. 21236
    Prev
    Next
    INDEX
    Explanations

    phrases relating to conflict and contradiction

    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
    2:0.10
    3:0.40
    4:0.14
    5:0.11
    6:0.02
    7:0.03
    8:0.02
    9:0.05
    10:0.01
    11:0.03
    Negative Logits
    Enlarge
    -4.98
     --
    -4.30
     —
    -4.28
     ―
    -3.77
    —
    -3.77
     ---
    -3.68
    --
    -3.65
    .--
    -3.63
    ,)
    -3.43
    ADVERTISEMENT
    -3.28
    POSITIVE LOGITS
    ".
    8.60
    ".[
    8.54
    ",
    8.54
     ",
    7.86
    !".
    7.47
    ?".
    7.15
     ".
    7.04
    )",
    6.97
    .",
    6.71
     organise
    6.59
    Activations Density 0.025%

    No Known Activations