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. 1-ATT-KK
    6. 6321
    Prev
    Next
    INDEX
    Explanations

    words related to competitive sports and achievement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    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
    1:0.07
    2:0.09
    3:0.05
    4:0.08
    5:0.09
    6:0.08
    7:0.12
    8:0.07
    9:0.06
    10:0.08
    11:0.09
    Negative Logits
     Representatives
    -1.59
     Authorities
    -1.54
    south
    -1.53
     Beijing
    -1.52
     Persons
    -1.50
     Officials
    -1.47
     Advis
    -1.44
     Bangladesh
    -1.42
     Serbia
    -1.42
     Islamabad
    -1.41
    POSITIVE LOGITS
     tease
    1.62
     Pixie
    1.56
     handwriting
    1.56
     comedic
    1.56
     ballet
    1.56
    ilogy
    1.53
     Whedon
    1.52
     Assassin
    1.51
     soundtrack
    1.50
     belie
    1.49
    Activations Density 0.000%

    No Known Activations