Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20632
    Prev
    Next
    INDEX
    Explanations

    specific terms and commands related to scripting and APIs

    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
    0:0.09
    1:0.04
    2:0.05
    3:0.04
    4:0.05
    5:0.07
    6:0.16
    7:0.03
    8:0.08
    9:0.28
    10:0.03
    11:0.03
    Negative Logits
     Eaton
    -4.10
     Feld
    -4.03
    ヘラ
    -3.64
     Frie
    -3.56
     Melt
    -3.50
     Milwaukee
    -3.38
    ANA
    -3.37
     Barrett
    -3.32
     Lauder
    -3.28
    luster
    -3.27
    POSITIVE LOGITS
    script
    7.39
     Script
    7.38
     script
    6.91
    scripts
    6.88
     scripts
    6.84
    Script
    6.69
     scripting
    5.78
    RIPT
    4.80
    javascript
    4.50
    cript
    4.48
    Activations Density 0.003%

    No Known Activations