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. 20617
    Prev
    Next
    INDEX
    Explanations

    information related to heating systems and their efficiency

    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
    0:0.19
    1:0.02
    2:0.19
    3:0.13
    4:0.04
    5:0.14
    6:0.06
    7:0.04
    8:0.05
    9:0.04
    10:0.03
    11:0.02
    Negative Logits
     Marks
    -2.93
     Unicode
    -2.26
    Transaction
    -2.25
     Arrows
    -2.21
     Scholar
    -2.20
     Spear
    -2.15
     Binary
    -2.14
     fragment
    -2.13
     Scholarship
    -2.05
     Represent
    -2.02
    POSITIVE LOGITS
     heater
    4.48
     cooling
    4.43
     heating
    4.29
     heat
    3.91
     therm
    3.88
     furnace
    3.84
     ventilation
    3.82
     temperature
    3.75
     humidity
    3.70
     refriger
    3.62
    Activations Density 0.271%

    No Known Activations