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. 5-ATT-KK
    6. 27457
    Prev
    Next
    INDEX
    Explanations

    mentions of the controversial figure Milo Yiannopoulos and events associated with him

    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
    0:0.05
    1:0.03
    2:0.06
    3:0.06
    4:0.06
    5:0.06
    6:0.06
    7:0.03
    8:0.04
    9:0.07
    10:0.32
    11:0.11
    Negative Logits
    foundland
    -1.66
     NAD
    -1.49
    sembly
    -1.48
     Hyundai
    -1.47
    uries
    -1.45
     Renault
    -1.41
     harmonic
    -1.40
     Stafford
    -1.39
     Rhythm
    -1.37
     AFC
    -1.34
    POSITIVE LOGITS
    iannopoulos
    1.56
    wiki
    1.45
    tumblr
    1.45
    wik
    1.43
    Cart
    1.41
     participating
    1.38
     pedoph
    1.37
     provocative
    1.37
     supporters
    1.36
     https
    1.35
    Activations Density 0.003%

    No Known Activations