© 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. 9-ATT-KK
    11. 12344
    Prev
    Next
    INDEX
    Explanations

    references to policies related to space activities and regulations in Australia

    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
    0:0.12
    1:0.03
    2:0.13
    3:0.11
    4:0.08
    5:0.10
    6:0.05
    7:0.10
    8:0.08
    9:0.05
    10:0.04
    11:0.05
    Negative Logits
     hanged
    -2.91
     booze
    -2.82
     gossip
    -2.67
    Laughs
    -2.59
    venge
    -2.55
     comedians
    -2.52
    abilia
    -2.52
    comed
    -2.51
     revenge
    -2.49
     weird
    -2.45
    POSITIVE LOGITS
     Implementation
    3.61
     Advisory
    3.48
     DOE
    3.31
     Assessment
    3.29
     methodological
    3.29
     Framework
    3.18
     CBO
    3.15
     stakeholders
    3.14
     Policy
    3.14
     Agenda
    3.09
    Activations Density 0.341%

    No Known Activations