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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3153
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to organizations

    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
    0:0.04
    1:0.03
    2:0.03
    3:0.04
    4:0.03
    5:0.05
    6:0.16
    7:0.03
    8:0.03
    9:0.41
    10:0.03
    11:0.05
    Negative Logits
     Pyr
    -3.40
     Pelosi
    -3.15
    APS
    -3.04
     Cadillac
    -3.00
     Pegasus
    -2.99
    Rog
    -2.97
     Pony
    -2.94
    phant
    -2.93
    waves
    -2.89
     Cly
    -2.88
    POSITIVE LOGITS
     International
    4.88
    International
    4.73
    international
    4.58
    ondon
    3.52
     international
    3.52
     Cong
    3.39
     Hague
    3.37
     ICC
    3.25
     ISO
    3.23
     HI
    3.21
    Activations Density 0.004%

    No Known Activations