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. 7584
    Prev
    Next
    INDEX
    Explanations

    terms related to referencing or pointers in programming

    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
    0:0.06
    1:0.07
    2:0.08
    3:0.06
    4:0.07
    5:0.09
    6:0.07
    7:0.09
    8:0.09
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
     NFC
    -3.08
     É
    -3.03
     PCR
    -2.83
     Café
    -2.60
     CAD
    -2.59
     Convers
    -2.58
     Finnish
    -2.54
     Anglic
    -2.54
    É
    -2.53
     Gospel
    -2.52
    POSITIVE LOGITS
    bors
    2.94
    dule
    2.75
    terness
    2.72
    ractions
    2.68
    ritch
    2.64
    dry
    2.62
    utonium
    2.57
    pell
    2.55
    Zen
    2.54
    iatus
    2.54
    Activations Density 0.000%

    No Known Activations