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. 3-ATT-KK
    6. 7738
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.10
    2:0.17
    3:0.09
    4:0.04
    5:0.05
    6:0.07
    7:0.08
    8:0.12
    9:0.05
    10:0.06
    11:0.08
    Negative Logits
    cake
    -1.22
    orks
    -1.13
    bal
    -1.07
    foreseen
    -1.06
    farious
    -1.06
    eli
    -1.05
    icals
    -1.04
    boats
    -1.03
    \">
    -1.02
    rolling
    -1.02
    POSITIVE LOGITS
    ��
    1.36
    -)
    1.25
     Earn
    1.20
    amon
    1.13
     multiplier
    1.11
     Kamp
    1.07
    Registered
    1.07
    )=
    1.05
     Billion
    1.05
     Memory
    1.05
    Activations Density 0.002%

    No Known Activations