© 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. 3-ATT-KK
    11. 11337
    Prev
    Next
    INDEX
    Explanations

    terms related to offshore oil and energy industries, including their economic and regulatory aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.07
    3:0.13
    4:0.02
    5:0.04
    6:0.14
    7:0.22
    8:0.05
    9:0.05
    10:0.07
    11:0.10
    Negative Logits
    ALSE
    -1.22
    acci
    -1.19
     TAMADRA
    -1.09
     horns
    -1.06
    Sov
    -1.03
     Silence
    -1.00
    Interstitial
    -0.99
     amplification
    -0.97
     stereotypical
    -0.97
     onstage
    -0.95
    POSITIVE LOGITS
    recy
    1.39
    merce
    1.22
    projects
    1.19
    ridor
    1.17
    vironments
    1.15
     intern
    1.14
    ="/
    1.14
    rencies
    1.12
    communication
    1.11
    gi
    1.09
    Activations Density 0.008%

    No Known Activations