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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3050
    Prev
    Next
    INDEX
    Explanations

    references to the "Ghostbusters" franchise, including its actors and films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.01
    2:0.12
    3:0.07
    4:0.03
    5:0.07
    6:0.10
    7:0.04
    8:0.14
    9:0.06
    10:0.06
    11:0.04
    Negative Logits
     Sudan
    -3.21
    igers
    -3.19
    heid
    -3.16
    beans
    -3.09
     Yemeni
    -3.07
    -->
    -3.03
    Saharan
    -3.00
     Ethiopian
    -3.00
    Alabama
    -2.96
     Erit
    -2.90
    POSITIVE LOGITS
     Ghostbusters
    8.99
    Ghost
    4.29
    busters
    3.92
     costumes
    3.75
     MGM
    3.64
     Zup
    3.45
     Myster
    3.44
     Leslie
    3.40
     Rudolph
    3.39
     ghosts
    3.37
    Activations Density 0.002%

    No Known Activations