© 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. 3-ATT-KK
    11. 13074
    Prev
    Next
    INDEX
    Explanations

    information related to fires, disasters, and emergencies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    reports of incidents involving fire or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.04
    2:0.08
    3:0.02
    4:0.05
    5:0.09
    6:0.09
    7:0.33
    8:0.06
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
     nic
    -1.33
    puter
    -1.27
    joice
    -1.27
     portfolios
    -1.26
     corners
    -1.21
     lect
    -1.15
     slots
    -1.14
     cabinets
    -1.13
     Printed
    -1.13
     Minion
    -1.13
    POSITIVE LOGITS
    ÃÂ
    1.49
     CBI
    1.38
     relocation
    1.33
    ipel
    1.26
     barr
    1.23
    aukee
    1.22
    ÃÂÃÂ
    1.22
     whistlebl
    1.22
    nings
    1.21
     intens
    1.20
    Activations Density 0.143%

    No Known Activations