© 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. 5-ATT-KK
    11. 43711
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to measurements or descriptions of size and shape

    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
    0:0.03
    1:0.06
    2:0.02
    3:0.03
    4:0.01
    5:0.54
    6:0.02
    7:0.02
    8:0.07
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
     Gors
    -1.78
     fir
    -1.63
    itech
    -1.61
    agna
    -1.60
     MGM
    -1.56
    \\\\\\\\
    -1.56
    FB
    -1.53
    OTAL
    -1.52
    wings
    -1.50
     Islanders
    -1.48
    POSITIVE LOGITS
     annotation
    1.62
     lett
    1.57
     Conscious
    1.50
     refers
    1.48
     contraction
    1.48
     transcript
    1.47
     organism
    1.42
     resume
    1.40
     Debt
    1.39
    Jen
    1.39
    Activations Density 0.785%

    No Known Activations