© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 12285
    Prev
    Next
    INDEX
    Explanations

    references to dates and statistics in sports contexts

    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
    0:0.07
    1:0.02
    2:0.03
    3:0.20
    4:0.17
    5:0.11
    6:0.06
    7:0.07
    8:0.03
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
    committee
    -2.26
    Whoever
    -2.23
    Fake
    -2.11
    ataka
    -2.11
    Pokemon
    -2.08
    pty
    -2.04
     misunder
    -2.03
    STAR
    -2.00
    Officials
    -1.98
    ]'
    -1.98
    POSITIVE LOGITS
     Bind
    2.18
     helm
    1.98
     ↑
    1.95
    ?",
    1.88
     {"
    1.85
    >(
    1.80
    ®,
    1.78
     ("
    1.75
     lifelong
    1.73
    zman
    1.72
    Activations Density 0.052%

    No Known Activations