Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27464
    Prev
    Next
    INDEX
    Explanations

    expressions of disappointment or surprise

    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
    0:0.08
    1:0.13
    2:0.03
    3:0.08
    4:0.03
    5:0.15
    6:0.05
    7:0.01
    8:0.13
    9:0.11
    10:0.08
    11:0.06
    Negative Logits
    20439
    -1.62
    climate
    -1.50
    onom
    -1.44
     Surviv
    -1.42
    urst
    -1.39
    assis
    -1.36
    issance
    -1.35
    ullivan
    -1.34
    ktop
    -1.32
    onut
    -1.32
    POSITIVE LOGITS
     Tags
    1.27
     …"
    1.24
     circled
    1.23
     knots
    1.22
    �
    1.17
     0004
    1.16
     XXX
    1.14
     Poker
    1.14
     POW
    1.14
     hanged
    1.13
    Activations Density 0.030%

    No Known Activations