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. 3088
    Prev
    Next
    INDEX
    Explanations

    references to major sporting events and their participants

    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
    0:0.07
    1:0.01
    2:0.17
    3:0.05
    4:0.04
    5:0.06
    6:0.08
    7:0.07
    8:0.27
    9:0.07
    10:0.03
    11:0.02
    Negative Logits
     Dise
    -3.58
     Droid
    -3.41
     Arkham
    -3.08
     Cerberus
    -2.97
    Desktop
    -2.91
    Serial
    -2.90
     Clone
    -2.87
     cider
    -2.84
    \">
    -2.81
    perties
    -2.79
    POSITIVE LOGITS
     Olympic
    7.35
     IOC
    7.32
     Olympics
    6.84
     Sochi
    6.45
     Olymp
    6.18
     medal
    5.53
     athletes
    5.50
     Athlet
    5.39
     medals
    5.17
     Mongolia
    5.17
    Activations Density 0.052%

    No Known Activations