© 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. 10-ATT-KK
    11. 8509
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court cases and filings

    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
    0:0.05
    1:0.05
    2:0.06
    3:0.04
    4:0.05
    5:0.03
    6:0.24
    7:0.27
    8:0.02
    9:0.02
    10:0.05
    11:0.06
    Negative Logits
     encour
    -2.33
     Baird
    -2.23
     McMaster
    -2.15
    assadors
    -2.12
     eleph
    -2.11
    bane
    -2.08
    elong
    -2.08
     recruited
    -2.08
    eele
    -2.07
    undai
    -2.02
    POSITIVE LOGITS
     filing
    3.25
     filed
    2.87
    ヴァ
    2.72
     filings
    2.58
    OTUS
    2.55
     lawy
    2.49
     Mayweather
    2.36
    metadata
    2.35
     Arpaio
    2.35
     ATF
    2.33
    Activations Density 0.053%

    No Known Activations