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. 10-ATT-KK
    6. 14686
    Prev
    Next
    INDEX
    Explanations

    details related to humanitarian aid efforts and the conditions in Haiti following a disaster

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.27
    1:0.04
    2:0.03
    3:0.08
    4:0.06
    5:0.02
    6:0.05
    7:0.14
    8:0.01
    9:0.04
    10:0.18
    11:0.03
    Negative Logits
     owl
    -3.82
    Miller
    -3.68
     Nuggets
    -3.62
     android
    -3.48
     NR
    -3.34
     Sirius
    -3.28
    Batman
    -3.18
    arettes
    -3.17
     Subaru
    -3.16
    etsk
    -3.16
    POSITIVE LOGITS
     Hait
    9.63
     Haitian
    9.52
     Haiti
    8.83
     Hispan
    6.70
     Dominican
    5.67
     Hond
    4.67
     Caribbean
    4.60
     Honduras
    4.26
     earthquake
    4.03
     Bahamas
    4.02
    Activations Density 0.010%

    No Known Activations