© 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. 9-ATT-KK
    11. 17773
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting elements, particularly in the context of state or location identifiers

    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
    0:0.05
    1:0.02
    2:0.05
    3:0.11
    4:0.06
    5:0.39
    6:0.04
    7:0.06
    8:0.04
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
     VIDEOS
    -3.28
    ↵
    -2.77
    SPONSORED
    -2.73
     Nanto
    -2.54
    xual
    -2.40
     bidding
    -2.39
     Crate
    -2.37
     tattoo
    -2.37
     plagiar
    -2.33
     Dungeons
    -2.32
    POSITIVE LOGITS
    aturdays
    3.10
    Pand
    3.07
    ((
    3.02
    Cent
    2.77
    Multi
    2.77
    iso
    2.76
    Simple
    2.74
    Here
    2.73
    ディ
    2.71
    �
    2.70
    Activations Density 0.407%

    No Known Activations