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. 7-ATT-KK
    6. 9376
    Prev
    Next
    INDEX
    Explanations

    references to essential resources and living conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.14
    1:0.07
    2:0.01
    3:0.12
    4:0.09
    5:0.14
    6:0.07
    7:0.05
    8:0.10
    9:0.11
    10:0.01
    11:0.03
    Negative Logits
     believer
    -2.05
     parody
    -1.89
     cameo
    -1.83
     Spy
    -1.75
     listener
    -1.75
     Deadpool
    -1.75
    quote
    -1.74
     Revis
    -1.72
     commenter
    -1.70
     Winner
    -1.68
    POSITIVE LOGITS
     ration
    2.21
     adequate
    2.04
     inadequate
    2.01
    adequ
    2.01
     necessities
    1.99
    Solution
    1.98
    ptoms
    1.96
     scarce
    1.93
     shelters
    1.92
     shortages
    1.92
    Activations Density 0.068%

    No Known Activations