© 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. 5-ATT-KK
    11. 17628
    Prev
    Next
    INDEX
    Explanations

    recurring symbols or characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.06
    2:0.06
    3:0.06
    4:0.04
    5:0.25
    6:0.04
    7:0.01
    8:0.28
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
     mathemat
    -2.20
     [&
    -1.76
     weap
    -1.75
     monop
    -1.73
     coerc
    -1.71
     incorpor
    -1.64
     commod
    -1.64
     chall
    -1.61
    ewater
    -1.58
     destro
    -1.58
    POSITIVE LOGITS
    abeth
    1.99
    endum
    1.86
    enario
    1.85
    avorite
    1.84
    session
    1.73
     Column
    1.69
    celona
    1.67
    untu
    1.63
    iverpool
    1.63
    ía
    1.62
    Activations Density 0.038%

    No Known Activations