© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-ATT-KK
    11. 2632
    Prev
    Next
    INDEX
    Explanations

    references to legal processes and issues related to justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.06
    2:0.06
    3:0.03
    4:0.06
    5:0.04
    6:0.18
    7:0.04
    8:0.08
    9:0.23
    10:0.02
    11:0.04
    Negative Logits
    Saudi
    -3.83
    949
    -3.65
     Saudis
    -3.53
     Sherman
    -3.50
     Saudi
    -3.50
    riott
    -3.46
     Sears
    -3.43
     Darrell
    -3.42
    rentice
    -3.42
    serial
    -3.37
    POSITIVE LOGITS
     Go
    6.32
     GO
    6.23
    GO
    6.01
    Go
    5.45
    go
    5.35
     Goo
    5.06
     GN
    4.79
     Gos
    4.48
     gol
    4.41
     Golem
    4.29
    Activations Density 0.008%

    No Known Activations