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. 3045
    Prev
    Next
    INDEX
    Explanations

    references to large groups or numbers of people participating in events or movements

    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
    0:0.08
    1:0.03
    2:0.06
    3:0.05
    4:0.07
    5:0.04
    6:0.26
    7:0.05
    8:0.11
    9:0.13
    10:0.03
    11:0.04
    Negative Logits
     Tyson
    -4.17
     Skinner
    -3.80
     Duff
    -3.77
     Hoffman
    -3.74
    eer
    -3.73
     Spur
    -3.72
     yog
    -3.72
     Benson
    -3.64
    EVA
    -3.62
     Franken
    -3.61
    POSITIVE LOGITS
     Catal
    10.52
    Catal
    9.80
     Catalonia
    7.01
     Catalan
    6.87
     Barcelona
    5.18
     Scarlet
    4.25
     Celt
    4.25
     Regist
    4.23
    chrom
    4.23
    celona
    4.04
    Activations Density 0.000%

    No Known Activations