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. 7460
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, names, and notable entities

    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
    0:0.45
    1:0.04
    2:0.03
    3:0.04
    4:0.04
    5:0.06
    6:0.02
    7:0.02
    8:0.11
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
    BuyableInstoreAndOnline
    -2.01
     ):
    -1.93
    MAT
    -1.73
    doi
    -1.72
     ↑
    -1.71
            
    -1.71
    ↵ 
    -1.68
     ).
    -1.68
    .)
    -1.66
    Subject
    -1.62
    POSITIVE LOGITS
    's
    2.12
    ]'
    1.90
    isoft
    1.87
     Corp
    1.71
    ptroller
    1.69
    lier
    1.67
     Investig
    1.65
    aida
    1.63
    kson
    1.58
     Inspector
    1.57
    Activations Density 0.022%

    No Known Activations