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. 20628
    Prev
    Next
    INDEX
    Explanations

    standalone letters and single-character identifiers

    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
    0:0.09
    1:0.05
    2:0.06
    3:0.09
    4:0.08
    5:0.05
    6:0.17
    7:0.06
    8:0.06
    9:0.15
    10:0.04
    11:0.05
    Negative Logits
     Steele
    -3.01
     Pry
    -2.84
     Sean
    -2.83
     Peter
    -2.77
    rave
    -2.71
     ·
    -2.63
     Sawyer
    -2.63
     Rowe
    -2.61
     Kate
    -2.60
     Wit
    -2.58
    POSITIVE LOGITS
     mills
    3.00
     dams
    2.99
     calves
    2.78
     ceremonies
    2.76
     militias
    2.69
     militar
    2.66
     miscar
    2.65
     ordinances
    2.63
     mamm
    2.63
     forests
    2.61
    Activations Density 0.000%

    No Known Activations