© 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. 5-ATT-KK
    6. 42697
    Prev
    Next
    INDEX
    Explanations

    awards and recognitions in the context of media or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.03
    2:0.06
    3:0.06
    4:0.06
    5:0.04
    6:0.04
    7:0.33
    8:0.04
    9:0.05
    10:0.13
    11:0.08
    Negative Logits
    lambda
    -1.84
     riff
    -1.75
    fuck
    -1.73
    ipel
    -1.73
    mare
    -1.66
     Wonderland
    -1.65
    punk
    -1.59
    aha
    -1.58
    character
    -1.57
    loop
    -1.55
    POSITIVE LOGITS
    orthy
    1.99
     scholarships
    1.97
     advis
    1.95
     prizes
    1.89
     legitimacy
    1.88
     citations
    1.86
    PDATE
    1.86
     awarding
    1.82
     prestigious
    1.80
     immunity
    1.76
    Activations Density 0.001%

    No Known Activations