© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 1101
    Prev
    Next
    INDEX
    Explanations

    references to oil spills and their consequences

    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
    0:0.17
    1:0.01
    2:0.27
    3:0.06
    4:0.03
    5:0.11
    6:0.04
    7:0.04
    8:0.12
    9:0.03
    10:0.03
    11:0.03
    Negative Logits
     chess
    -2.67
     Krish
    -2.52
    ���
    -2.52
     Chess
    -2.46
     Arcade
    -2.43
    abetic
    -2.40
    Psych
    -2.40
     undefeated
    -2.38
     Psychiat
    -2.33
    abet
    -2.33
    POSITIVE LOGITS
     spill
    5.09
     spills
    4.90
     spilled
    4.45
     spilling
    3.95
     cleanup
    3.90
     BP
    3.36
    Oil
    3.34
     Gulf
    3.31
     Exxon
    3.29
     ashore
    3.27
    Activations Density 0.024%

    No Known Activations