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. 5-ATT-KK
    6. 7392
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and values associated with sports scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.11
    2:0.15
    3:0.08
    4:0.04
    5:0.08
    6:0.03
    7:0.01
    8:0.06
    9:0.12
    10:0.04
    11:0.06
    Negative Logits
    pmwiki
    -1.93
    quickShipAvailable
    -1.65
    ailability
    -1.59
    actionDate
    -1.59
    beit
    -1.55
     GOODMAN
    -1.49
    NetMessage
    -1.45
    annel
    -1.45
    %%%%
    -1.44
    eger
    -1.44
    POSITIVE LOGITS
     Qi
    1.47
     Inn
    1.44
     Schwar
    1.12
     Pokémon
    1.12
     Hollow
    1.11
     guesses
    1.10
     Crus
    1.09
     TH
    1.09
     Pokemon
    1.08
     Occ
    1.08
    Activations Density 0.072%

    No Known Activations