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. 11328
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and player transactions

    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
    1:0.02
    2:0.06
    3:0.03
    4:0.06
    5:0.03
    6:0.27
    7:0.04
    8:0.08
    9:0.20
    10:0.03
    11:0.04
    Negative Logits
     Delta
    -4.00
    Delta
    -3.97
    ンジ
    -3.91
     Starship
    -3.75
     Turing
    -3.65
    diagn
    -3.50
     DSM
    -3.49
     starship
    -3.48
     Spectre
    -3.47
    antis
    -3.25
    POSITIVE LOGITS
     Ol
    10.40
    Ol
    9.76
     Olson
    6.46
     ol
    6.37
     OL
    6.13
     Oliver
    5.74
     Olsen
    5.48
     Anna
    5.03
    OL
    4.84
     Ori
    4.79
    Activations Density 0.006%

    No Known Activations