© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 12391
    Prev
    Next
    INDEX
    Explanations

    references to legal and investigative contexts

    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
    0:0.17
    1:0.05
    2:0.07
    3:0.05
    4:0.05
    5:0.06
    6:0.13
    7:0.03
    8:0.04
    9:0.23
    10:0.03
    11:0.03
    Negative Logits
     Morty
    -4.11
     Poker
    -4.01
     Rory
    -3.79
     Louie
    -3.75
     Anarchy
    -3.72
     Ic
    -3.60
     Bron
    -3.51
     SN
    -3.46
    Ro
    -3.39
     Barker
    -3.38
    POSITIVE LOGITS
     document
    6.85
    document
    6.73
     documents
    6.58
    Document
    6.38
     Document
    6.14
     Documents
    6.00
    doc
    5.99
    Documents
    5.94
     DOC
    5.31
     doc
    5.19
    Activations Density 0.010%

    No Known Activations