© 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. 28671
    Prev
    Next
    INDEX
    Explanations

    expressions of well-wishes and positive sentiments

    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
    0:0.01
    1:0.01
    2:0.14
    3:0.09
    4:0.19
    5:0.02
    6:0.05
    7:0.30
    8:0.03
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
     subt
    -1.59
    ighting
    -1.55
    encers
    -1.53
    itures
    -1.50
    ories
    -1.50
    enser
    -1.49
    matter
    -1.48
    sheets
    -1.45
    henko
    -1.45
    utenberg
    -1.44
    POSITIVE LOGITS
     afterlife
    1.81
     eternity
    1.71
     immortality
    1.63
     martyr
    1.62
     nostalg
    1.61
     Bye
    1.54
     chance
    1.50
     blessing
    1.50
     Schne
    1.50
     blessings
    1.49
    Activations Density 0.002%

    No Known Activations