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. 2-ATT-KK
    6. 13755
    Prev
    Next
    INDEX
    Explanations

    controversial topics or debates related to politics and society, especially in the context of solutions or arguments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.05
    2:0.09
    3:0.06
    4:0.05
    5:0.08
    6:0.03
    7:0.07
    8:0.08
    9:0.26
    10:0.08
    11:0.04
    Negative Logits
    usercontent
    -1.32
     Tile
    -1.21
    ��極
    -1.20
    ondo
    -1.18
     Hig
    -1.17
     Seraph
    -1.17
    amina
    -1.16
     seaf
    -1.15
     Spartans
    -1.11
    rete
    -1.11
    POSITIVE LOGITS
    wcs
    1.39
     debated
    1.38
    enegger
    1.30
     Debate
    1.20
    jri
    1.19
     Conservatives
    1.19
     chaired
    1.19
    proven
    1.17
     Topic
    1.17
    quickShipAvailable
    1.16
    Activations Density 0.042%

    No Known Activations