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. 3112
    Prev
    Next
    INDEX
    Explanations

    political terms and critiques associated with defense spending and legislative actions

    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
    0:0.05
    1:0.02
    2:0.04
    3:0.15
    4:0.15
    5:0.10
    6:0.06
    7:0.05
    8:0.03
    9:0.02
    10:0.23
    11:0.05
    Negative Logits
     dece
    -1.99
     suppressed
    -1.98
     consequ
    -1.98
     "…
    -1.97
     recently
    -1.95
     favour
    -1.89
     wonders
    -1.87
     benefiting
    -1.86
     afore
    -1.85
     benef
    -1.85
    POSITIVE LOGITS
    ullivan
    2.33
    inventoryQuantity
    2.29
    azard
    2.25
    ertodd
    2.21
    atican
    2.20
    vernight
    2.19
     Cummings
    2.16
    imaru
    2.16
    ahime
    2.11
    amber
    2.09
    Activations Density 0.020%

    No Known Activations