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. 3-ATT-KK
    6. 8632
    Prev
    Next
    INDEX
    Explanations

    references to government positions, particularly related to the Secretary of State and other executive roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.06
    2:0.12
    3:0.26
    4:0.01
    5:0.01
    6:0.12
    7:0.10
    8:0.03
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
    nai
    -1.11
    ndra
    -1.06
    jad
    -0.98
     flick
    -0.96
    opian
    -0.96
    arkable
    -0.89
    pson
    -0.87
     Zan
    -0.86
    fu
    -0.86
    rero
    -0.85
    POSITIVE LOGITS
     Treasury
    1.29
    gov
    1.17
    interstitial
    1.12
    backer
    1.03
    hyde
    1.03
     Gifts
    0.97
    ichick
    0.96
    �士
    0.95
    Correction
    0.94
    taboola
    0.94
    Activations Density 0.016%

    No Known Activations