© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-ATT-KK
    11. 19471
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to digital privacy and security

    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
    0:0.22
    1:0.28
    2:0.03
    3:0.03
    4:0.02
    5:0.19
    6:0.03
    7:0.01
    8:0.06
    9:0.04
    10:0.03
    11:0.02
    Negative Logits
    Merit
    -2.65
    mire
    -2.26
    ival
    -2.26
    isner
    -2.25
    atch
    -2.20
    isi
    -2.19
    Chain
    -2.18
    blade
    -2.18
    gram
    -2.17
    SPONSORED
    -2.14
    POSITIVE LOGITS
     Zin
    2.27
     Aurora
    2.26
     Huntington
    2.18
     Ny
    2.16
     none
    2.13
     Ele
    2.11
     Bri
    2.10
     Angry
    2.08
     Kron
    2.05
     UCS
    2.05
    Activations Density 0.105%

    No Known Activations