© 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. 3-ATT-KK
    11. 8195
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or incredulity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.04
    2:0.13
    3:0.03
    4:0.02
    5:0.04
    6:0.11
    7:0.15
    8:0.07
    9:0.09
    10:0.09
    11:0.16
    Negative Logits
    urated
    -1.19
    ledged
    -1.15
    rolled
    -1.09
    itored
    -1.09
    ivable
    -1.08
    untled
    -1.06
     preferred
    -1.05
    itute
    -0.99
    lain
    -0.99
    rette
    -0.98
    POSITIVE LOGITS
    Reviewer
    1.47
     Dot
    1.16
     Chop
    1.03
     Plaint
    1.00
    ????????
    0.96
     squirrel
    0.96
     Niet
    0.93
    Snake
    0.93
     Defendant
    0.92
    plet
    0.91
    Activations Density 0.058%

    No Known Activations