© 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 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. 2007
    Prev
    Next
    INDEX
    Explanations

    references to illegal or unethical activities related to financial transactions

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.15
    4:0.08
    5:0.06
    6:0.03
    7:0.06
    8:0.05
    9:0.14
    10:0.15
    11:0.10
    Negative Logits
    ocalypse
    -1.44
     Zombies
    -1.37
    Favorite
    -1.37
    anski
    -1.34
     Lovecraft
    -1.32
     apocalypse
    -1.29
    insky
    -1.28
    ovies
    -1.27
    osaurus
    -1.27
    orge
    -1.26
    POSITIVE LOGITS
     CBI
    1.35
     enqu
    1.30
     authorised
    1.29
     mediation
    1.27
     Inquiry
    1.27
     labou
    1.26
     plea
    1.25
     Malays
    1.21
     assisting
    1.19
    ■
    1.18
    Activations Density 0.450%

    No Known Activations