© 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. 22626
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to incidents involving police violence and systemic injustice

    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
    2:0.05
    3:0.06
    4:0.23
    5:0.28
    6:0.03
    7:0.03
    8:0.02
    9:0.13
    10:0.02
    11:0.04
    Negative Logits
    etheless
    -3.71
    20439
    -3.55
     largeDownload
    -3.55
    VERTISEMENT
    -3.53
     «
    -3.08
     obser
    -2.94
     '[
    -2.90
    mittedly
    -2.82
    nown
    -2.78
     altogether
    -2.78
    POSITIVE LOGITS
    !"
    6.69
    !",
    6.33
    !!"
    5.64
    !".
    5.32
    ;"
    5.02
    !'"
    4.98
    ";
    4.47
    ?!"
    4.44
    "!
    4.20
    !?"
    4.17
    Activations Density 0.046%

    No Known Activations