© 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. 9-ATT-KK
    11. 14991
    Prev
    Next
    INDEX
    Explanations

    numeric values and their associations in the text

    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
    1:0.01
    2:0.03
    3:0.19
    4:0.02
    5:0.04
    6:0.05
    7:0.03
    8:0.02
    9:0.01
    10:0.49
    11:0.03
    Negative Logits
     backlog
    -2.01
     Ruk
    -1.83
     glim
    -1.75
     rightful
    -1.64
     begg
    -1.60
    uld
    -1.59
     overrun
    -1.58
    icken
    -1.57
     stranded
    -1.57
     Corpse
    -1.56
    POSITIVE LOGITS
    )."
    4.90
    ).
    4.79
    .).
    4.68
    ),"
    4.66
     ).
    4.55
    )!
    4.43
    !).
    4.38
    ?).
    4.37
    ).[
    4.31
    %).
    3.86
    Activations Density 0.314%

    No Known Activations