© 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. 21002
    Prev
    Next
    INDEX
    Explanations

    references to music and film production roles and activities

    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
    0:0.11
    1:0.08
    2:0.06
    3:0.05
    4:0.04
    5:0.02
    6:0.23
    7:0.11
    8:0.02
    9:0.05
    10:0.07
    11:0.10
    Negative Logits
    Price
    -3.03
     Patriot
    -2.89
     Sawyer
    -2.54
    agic
    -2.51
     Kingston
    -2.50
     Gaw
    -2.47
     Round
    -2.46
     bumper
    -2.45
    Round
    -2.42
    TPP
    -2.41
    POSITIVE LOGITS
     directors
    5.64
     director
    5.53
    Director
    5.47
     Directors
    5.39
     Director
    5.04
    director
    5.01
     directing
    4.25
    Direct
    3.90
     Directorate
    3.86
    direct
    3.44
    Activations Density 0.014%

    No Known Activations