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. 9-ATT-KK
    6. 20636
    Prev
    Next
    INDEX
    Explanations

    questions regarding governmental policies and actions, particularly related to transparency and regulation

    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
    0:0.10
    1:0.04
    2:0.09
    3:0.07
    4:0.09
    5:0.07
    6:0.11
    7:0.05
    8:0.15
    9:0.09
    10:0.02
    11:0.07
    Negative Logits
     organise
    -3.32
     tyres
    -3.26
     Cardiff
    -3.16
     harbour
    -3.05
    elaide
    -2.95
    colour
    -2.94
     whisky
    -2.94
     tyre
    -2.93
    bour
    -2.93
     Swansea
    -2.90
    POSITIVE LOGITS
     HHS
    5.38
     DOJ
    5.14
     DHS
    4.92
     DOD
    4.44
     congressional
    4.44
     Obama
    4.42
     DOE
    4.30
     feds
    4.27
     federal
    4.24
     Congressional
    4.17
    Activations Density 0.266%

    No Known Activations