© 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. 26285
    Prev
    Next
    INDEX
    Explanations

    references to laws, regulations, and legal implications

    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
    0:0.09
    1:0.03
    2:0.02
    3:0.07
    4:0.04
    5:0.05
    6:0.03
    7:0.05
    8:0.05
    9:0.37
    10:0.10
    11:0.06
    Negative Logits
    udeb
    -1.99
    lehem
    -1.98
    ENA
    -1.97
    Rew
    -1.93
    %%%%
    -1.85
    owe
    -1.84
     fixme
    -1.81
    ~~~~
    -1.80
    inez
    -1.77
    endif
    -1.75
    POSITIVE LOGITS
     stockp
    1.88
     Hirosh
    1.76
     SG
    1.74
     Gins
    1.72
    otom
    1.69
     mastered
    1.62
     incorporated
    1.60
     appearing
    1.57
     pupils
    1.57
     outper
    1.56
    Activations Density 0.045%

    No Known Activations