© 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. 44066
    Prev
    Next
    INDEX
    Explanations

    references to solutions or workarounds for problems

    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
    0:0.02
    1:0.02
    2:0.07
    3:0.05
    4:0.32
    5:0.02
    6:0.06
    7:0.27
    8:0.03
    9:0.02
    10:0.04
    11:0.04
    Negative Logits
    emale
    -1.71
    aughtered
    -1.65
    ploma
    -1.57
    Downloadha
    -1.56
     Marketable
    -1.55
    ateurs
    -1.51
    inally
    -1.50
    ruits
    -1.50
    MET
    -1.43
    onement
    -1.43
    POSITIVE LOGITS
     loophole
    1.88
     anonymity
    1.87
     loopholes
    1.83
     notion
    1.79
     pesky
    1.78
     boundaries
    1.72
     bounds
    1.69
     recess
    1.67
     confines
    1.66
     discomfort
    1.64
    Activations Density 0.003%

    No Known Activations