© 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. 3104
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "at least" followed by a number or quantity

    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
    0:0.02
    1:0.02
    2:0.35
    3:0.06
    4:0.07
    5:0.03
    6:0.11
    7:0.05
    8:0.04
    9:0.03
    10:0.06
    11:0.09
    Negative Logits
     Cho
    -1.63
    の�
    -1.60
     Yok
    -1.60
     mo
    -1.59
     Legacy
    -1.58
     Stall
    -1.57
     Rossi
    -1.56
     Pike
    -1.49
     Nau
    -1.47
     replied
    -1.47
    POSITIVE LOGITS
    vity
    1.91
    heric
    1.83
     ILCS
    1.72
    wave
    1.70
    ulz
    1.64
     purposes
    1.63
    antz
    1.61
    idious
    1.57
    umatic
    1.56
    oths
    1.54
    Activations Density 0.012%

    No Known Activations