© 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. 3-ATT-KK
    11. 12169
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of the federal government

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

    references to the federal government and its actions or implications

    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
    0:0.07
    1:0.02
    2:0.10
    3:0.05
    4:0.03
    5:0.03
    6:0.32
    7:0.09
    8:0.05
    9:0.03
    10:0.10
    11:0.05
    Negative Logits
     Kik
    -1.32
    byn
    -1.27
     Sharks
    -1.23
     mos
    -1.19
    ictions
    -1.11
    Sov
    -1.08
     Predators
    -1.05
     Schl
    -1.04
     Malk
    -1.04
     Zan
    -1.03
    POSITIVE LOGITS
    arthed
    1.36
    asury
    1.31
    orate
    1.30
    ptroller
    1.26
    opa
    1.23
     treasury
    1.18
     subsid
    1.18
    cade
    1.17
     grate
    1.17
    sembly
    1.17
    Activations Density 0.020%

    No Known Activations