© 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. 12943
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant or notable situation

    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
    0:0.09
    1:0.06
    2:0.04
    3:0.05
    4:0.04
    5:0.03
    6:0.08
    7:0.38
    8:0.03
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
     Clarke
    -2.83
     Dixon
    -2.82
     Dund
    -2.81
     Dawson
    -2.76
     Cummings
    -2.75
     Ced
    -2.66
     Davies
    -2.61
     Stam
    -2.59
     Dill
    -2.56
    Li
    -2.52
    POSITIVE LOGITS
     Magnet
    2.44
    ��
    2.35
    "],"
    2.35
     fertilizer
    2.33
     magnet
    2.30
    arget
    2.27
     rockets
    2.26
    apult
    2.25
    forward
    2.23
    タ
    2.19
    Activations Density 0.005%

    No Known Activations