© 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. 10-ATT-KK
    11. 16710
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal sentencing and criminal charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.04
    3:0.16
    4:0.09
    5:0.04
    6:0.08
    7:0.24
    8:0.02
    9:0.09
    10:0.06
    11:0.05
    Negative Logits
     resolutions
    -2.05
     Caption
    -1.99
     anchors
    -1.91
     certs
    -1.91
     Dodd
    -1.91
    Reply
    -1.90
     Showdown
    -1.90
     manufact
    -1.88
     fram
    -1.87
     spills
    -1.85
    POSITIVE LOGITS
     parole
    3.20
    ora
    2.47
     pard
    2.43
    oran
    2.30
     pardon
    2.28
    BAT
    2.23
     Vaugh
    2.18
    IOR
    2.16
     Uzbek
    2.15
    olphin
    2.15
    Activations Density 0.197%

    No Known Activations