© 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. 9193
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intent or purpose related to law and legal actions

    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
    0:0.01
    1:0.02
    2:0.04
    3:0.29
    4:0.01
    5:0.02
    6:0.06
    7:0.16
    8:0.05
    9:0.08
    10:0.05
    11:0.15
    Negative Logits
    ivia
    -1.46
    soDeliveryDate
    -1.27
    Center
    -1.26
    imar
    -1.24
     ILCS
    -1.24
    Lab
    -1.23
     largeDownload
    -1.21
    ournals
    -1.20
    acan
    -1.19
    Flo
    -1.18
    POSITIVE LOGITS
     Sacrifice
    1.32
    テ
    1.25
     topp
    1.22
     reserv
    1.22
     arrang
    1.21
     omission
    1.21
     deceive
    1.19
     sacrifice
    1.16
     abst
    1.15
     BDS
    1.12
    Activations Density 0.012%

    No Known Activations