© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 12571
    Prev
    Next
    INDEX
    Explanations

    sports-related statistics and accomplishments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    performance metrics related to sports statistics

    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
    1:0.04
    2:0.10
    3:0.02
    4:0.06
    5:0.09
    6:0.14
    7:0.08
    8:0.06
    9:0.05
    10:0.08
    11:0.18
    Negative Logits
     ⓘ
    -1.48
    ebook
    -1.31
     webpage
    -1.31
    cknow
    -1.28
    ortment
    -1.28
     homepage
    -1.26
    ople
    -1.26
    orah
    -1.24
    ibliography
    -1.24
     Desk
    -1.23
    POSITIVE LOGITS
     apiece
    1.60
     consecut
    1.58
     consecutive
    1.58
     totaling
    1.44
     averaging
    1.43
     starters
    1.37
     overtime
    1.35
    phies
    1.35
     unbeaten
    1.34
     defeating
    1.27
    Activations Density 0.091%

    No Known Activations