© 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. 13263
    Prev
    Next
    INDEX
    Explanations

    key events and significant actions related to performances in sports and other activities

    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
    0:0.16
    1:0.11
    2:0.04
    3:0.03
    4:0.02
    5:0.02
    6:0.12
    7:0.10
    8:0.01
    9:0.03
    10:0.29
    11:0.02
    Negative Logits
    cius
    -3.32
    XM
    -3.25
     Pence
    -3.19
    ��
    -3.13
    Mp
    -3.07
    urdue
    -3.06
    pill
    -3.04
    Xi
    -3.03
     XT
    -3.00
     HIP
    -2.98
    POSITIVE LOGITS
     Ber
    10.62
    Ber
    9.03
     ber
    5.66
     Berger
    5.44
     Bur
    4.17
     Berry
    4.15
     Ger
    4.05
     Berg
    4.02
     Berlin
    3.88
     Berkeley
    3.80
    Activations Density 0.017%

    No Known Activations