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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 7542
    Prev
    Next
    INDEX
    Explanations

    names of key political figures and officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.19
    3:0.07
    4:0.04
    5:0.04
    6:0.05
    7:0.03
    8:0.07
    9:0.04
    10:0.14
    11:0.24
    Negative Logits
    office
    -1.64
    ghazi
    -1.57
     Presidency
    -1.50
    judicial
    -1.50
     presidency
    -1.50
    omaly
    -1.47
     amen
    -1.43
     captivity
    -1.42
     Mubarak
    -1.42
    defense
    -1.39
    POSITIVE LOGITS
    �醒
    1.68
    umers
    1.54
    ebted
    1.48
    ��
    1.48
    )=(
    1.42
    Weather
    1.39
    ixt
    1.33
     threaded
    1.32
    yrics
    1.32
    �
    1.32
    Activations Density 0.009%

    No Known Activations