© 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. 18452
    Prev
    Next
    INDEX
    Explanations

    mentions of mock drafts in relation to various subjects

    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
    0:0.11
    1:0.03
    2:0.09
    3:0.05
    4:0.03
    5:0.05
    6:0.13
    7:0.04
    8:0.05
    9:0.30
    10:0.03
    11:0.03
    Negative Logits
     Clancy
    -3.73
     Colomb
    -3.69
     Agu
    -3.45
     Div
    -3.29
     Divinity
    -3.26
    Div
    -3.12
     Cao
    -3.10
    ô
    -3.05
     hepatitis
    -3.05
     Thornton
    -3.01
    POSITIVE LOGITS
     Mock
    8.51
     mock
    7.99
     mocking
    5.88
     mocked
    5.75
     mockery
    5.19
    ock
    4.77
     puppet
    4.65
    uppet
    4.40
    fake
    4.34
     sock
    4.26
    Activations Density 0.001%

    No Known Activations