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. 8518
    Prev
    Next
    INDEX
    Explanations

    mentions of film and entertainment production companies

    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
    0:0.09
    1:0.15
    2:0.08
    3:0.02
    4:0.12
    5:0.08
    6:0.07
    7:0.09
    8:0.06
    9:0.06
    10:0.08
    11:0.03
    Negative Logits
     ­
    -1.21
    SPONSORED
    -1.20
    ibly
    -1.09
    ["
    -1.07
    entimes
    -1.07
     eyeb
    -1.06
    Ont
    -1.06
    ]."
    -1.06
    ially
    -1.04
     batter
    -1.03
    POSITIVE LOGITS
     ⓘ
    1.55
     Released
    1.24
     Shrine
    1.22
     Featuring
    1.15
     Moonlight
    1.14
     Variant
    1.11
     Volume
    1.08
     Tablet
    1.07
     Converted
    1.05
     Frontier
    1.04
    Activations Density 0.298%

    No Known Activations