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. 7590
    Prev
    Next
    INDEX
    Explanations

    references to the Air Force and its associated terminology

    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
    0:0.13
    1:0.05
    2:0.15
    3:0.07
    4:0.06
    5:0.07
    6:0.06
    7:0.07
    8:0.11
    9:0.05
    10:0.06
    11:0.07
    Negative Logits
     Dairy
    -2.83
     Ariel
    -2.50
     crown
    -2.45
     Blooming
    -2.40
     Disney
    -2.38
    †
    -2.37
     Marqu
    -2.36
     Frozen
    -2.35
     Geral
    -2.32
     Candy
    -2.31
    POSITIVE LOGITS
     Reconstruction
    2.79
    hex
    2.73
    philis
    2.71
     Cthulhu
    2.50
     pilots
    2.45
    ittal
    2.44
     debugging
    2.42
    etsk
    2.41
     Gork
    2.38
     Hacker
    2.37
    Activations Density 0.000%

    No Known Activations