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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10570
    Prev
    Next
    INDEX
    Explanations

    references to fossil fuels and their impact on energy production and the environment

    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
    0:0.08
    1:0.02
    2:0.09
    3:0.12
    4:0.02
    5:0.10
    6:0.02
    7:0.34
    8:0.07
    9:0.02
    10:0.03
    11:0.02
    Negative Logits
    prototype
    -2.22
     Ü
    -2.20
    coe
    -2.20
    REDACTED
    -2.20
    ploma
    -2.14
     Duff
    -2.11
    raltar
    -2.08
     Oo
    -2.07
    xtap
    -2.06
    interstitial
    -2.03
    POSITIVE LOGITS
     wildfires
    2.38
     solar
    2.38
     metals
    2.36
     livestock
    2.33
     groundwater
    2.33
     renewables
    2.31
     biomass
    2.27
     carbon
    2.27
     protects
    2.27
     reservoirs
    2.24
    Activations Density 0.101%

    No Known Activations