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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 44319
    Prev
    Next
    INDEX
    Explanations

    phrases related to time durations and waiting periods

    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
    2:0.20
    3:0.04
    4:0.11
    5:0.03
    6:0.05
    7:0.16
    8:0.04
    9:0.04
    10:0.14
    11:0.10
    Negative Logits
    ツ
    -1.69
     Teaching
    -1.40
     playable
    -1.39
     Areas
    -1.38
    Space
    -1.35
    qqa
    -1.32
     diagrams
    -1.32
     VII
    -1.32
     References
    -1.27
     Jackets
    -1.26
    POSITIVE LOGITS
    thouse
    1.89
    ourt
    1.85
     lest
    1.80
     nervously
    1.62
     unsuccessfully
    1.54
    swer
    1.51
    anwhile
    1.48
    mony
    1.48
    arna
    1.47
     lawy
    1.46
    Activations Density 0.002%

    No Known Activations