© 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. 43848
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rare" and phrases associated with rarity

    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
    0:0.01
    1:0.01
    2:0.07
    3:0.08
    4:0.11
    5:0.03
    6:0.06
    7:0.37
    8:0.02
    9:0.02
    10:0.08
    11:0.08
    Negative Logits
    uliffe
    -1.97
    ohan
    -1.55
     spir
    -1.45
    jad
    -1.45
    xon
    -1.45
    ascript
    -1.44
    agall
    -1.42
    aintain
    -1.36
    ressing
    -1.31
    heartedly
    -1.31
    POSITIVE LOGITS
     occurrence
    1.75
    Uncommon
    1.70
     Royale
    1.53
     Rare
    1.51
    Lot
    1.48
    arthed
    1.41
     Classic
    1.41
     Millennials
    1.41
     rare
    1.38
     Niet
    1.33
    Activations Density 0.014%

    No Known Activations