© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 12315
    Prev
    Next
    INDEX
    Explanations

    references to environmental disasters and the companies involved in them

    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
    0:0.22
    1:0.01
    2:0.15
    3:0.07
    4:0.03
    5:0.09
    6:0.03
    7:0.05
    8:0.24
    9:0.02
    10:0.03
    11:0.01
    Negative Logits
     Unic
    -3.12
     HTC
    -3.05
    �
    -2.96
    keyes
    -2.91
    ş
    -2.81
     Loll
    -2.73
     Flavoring
    -2.70
    FactoryReloaded
    -2.69
     Giov
    -2.65
    龍�
    -2.62
    POSITIVE LOGITS
     BP
    6.03
     Gulf
    4.34
    BP
    4.20
     oil
    3.83
     drilling
    3.67
     Exxon
    3.63
     offshore
    3.54
     gulf
    3.53
     Shell
    3.50
    Oil
    3.42
    Activations Density 0.029%

    No Known Activations