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. 7655
    Prev
    Next
    INDEX
    Explanations

    segments related to technical computer operations and connectivity issues

    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
    0:0.10
    1:0.04
    2:0.07
    3:0.04
    4:0.05
    5:0.05
    6:0.20
    7:0.04
    8:0.03
    9:0.26
    10:0.03
    11:0.04
    Negative Logits
     Baal
    -4.13
     Ezekiel
    -3.95
     Cassidy
    -3.78
     Katrina
    -3.65
     Sanctuary
    -3.65
     Pride
    -3.55
     Tuls
    -3.55
     Fest
    -3.49
     Gabriel
    -3.48
     Rath
    -3.37
    POSITIVE LOGITS
     Computer
    7.54
    Computer
    7.52
     computers
    7.19
     computer
    7.00
     Comput
    6.63
    computer
    6.62
    puters
    6.09
     computing
    6.07
     Computing
    5.83
    puter
    5.49
    Activations Density 0.010%

    No Known Activations