© 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. 27671
    Prev
    Next
    INDEX
    Explanations

    details about music events and venues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.11
    1:0.04
    2:0.10
    3:0.16
    4:0.11
    5:0.05
    6:0.03
    7:0.02
    8:0.04
    9:0.11
    10:0.10
    11:0.08
    Negative Logits
     swayed
    -1.71
    opian
    -1.62
     psychologists
    -1.62
     femin
    -1.62
     veterin
    -1.61
    エル
    -1.55
    の魔
    -1.53
     immune
    -1.52
     wedd
    -1.52
    channelAvailability
    -1.51
    POSITIVE LOGITS
     Festival
    1.81
    istration
    1.76
     Ferry
    1.74
     Feast
    1.70
     Ep
    1.66
     Concert
    1.65
     Dinner
    1.61
     Tours
    1.59
     Rem
    1.56
     Fest
    1.54
    Activations Density 0.010%

    No Known Activations