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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22979
    Prev
    Next
    INDEX
    Explanations

    information related to sports transfers and financial figures

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

    high-value financial transactions and figures related to sports transfers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.07
    2:0.06
    3:0.10
    4:0.04
    5:0.11
    6:0.06
    7:0.10
    8:0.04
    9:0.11
    10:0.11
    11:0.05
    Negative Logits
    NetMessage
    -1.06
    onom
    -1.05
    hing
    -1.04
     VID
    -1.02
    ☆
    -1.00
     Kern
    -0.99
     citiz
    -0.98
    ork
    -0.97
     BLACK
    -0.97
     POV
    -0.96
    POSITIVE LOGITS
     (£
    1.90
     £
    1.45
     Thames
    1.27
    /$
    1.26
     defence
    1.14
    £
    1.12
     ensu
    1.10
     tyres
    1.05
     offence
    1.05
     Wembley
    1.04
    Activations Density 0.063%

    No Known Activations