© 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. 43778
    Prev
    Next
    INDEX
    Explanations

    instances of the words "surprisingly" and "unsurprisingly" along with their related context

    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
    3:0.13
    4:0.07
    5:0.03
    6:0.03
    7:0.32
    8:0.04
    9:0.05
    10:0.07
    11:0.10
    Negative Logits
    ascript
    -1.82
    acebook
    -1.67
    gdala
    -1.65
    icrobial
    -1.65
    inav
    -1.65
    wrap
    -1.63
    agall
    -1.59
    mercial
    -1.55
    yip
    -1.51
    istries
    -1.50
    POSITIVE LOGITS
     criticism
    1.50
     criticisms
    1.28
     Campus
    1.28
     occurrence
    1.25
     retiring
    1.24
     Decay
    1.24
     Participant
    1.23
     scorn
    1.22
     complaints
    1.21
     Bucc
    1.21
    Activations Density 0.004%

    No Known Activations