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. 7695
    Prev
    Next
    INDEX
    Explanations

    references to sports victories and match results

    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
    0:0.04
    1:0.02
    2:0.05
    3:0.20
    4:0.03
    5:0.07
    6:0.02
    7:0.04
    8:0.09
    9:0.01
    10:0.35
    11:0.02
    Negative Logits
     concurrently
    -2.34
    cffff
    -2.07
     burner
    -2.07
     spor
    -1.97
    neys
    -1.95
     frequently
    -1.95
     fronts
    -1.93
     peppers
    -1.89
     regularly
    -1.89
    asionally
    -1.88
    POSITIVE LOGITS
     victory
    2.60
     prevailed
    2.42
     prevail
    2.36
     convincing
    2.30
     superiority
    2.17
    ERROR
    2.06
     Congratulations
    2.02
     unanim
    2.01
     defeat
    1.99
     rout
    1.96
    Activations Density 0.076%

    No Known Activations