© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28580
    Prev
    Next
    INDEX
    Explanations

    concepts related to the passage of time and significant time markers

    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
    2:0.08
    3:0.33
    4:0.12
    5:0.04
    6:0.02
    7:0.08
    8:0.04
    9:0.05
    10:0.07
    11:0.07
    Negative Logits
    ?]
    -2.19
    ?,
    -1.97
    ?",
    -1.97
    sic
    -1.93
    ?"
    -1.83
     [*]
    -1.75
    Correct
    -1.73
    )"
    -1.73
     ¶
    -1.68
     [-
    -1.65
    POSITIVE LOGITS
     Canaver
    1.92
     McLaren
    1.68
    rollers
    1.68
     Phelps
    1.61
     crammed
    1.60
     Coco
    1.55
     Cele
    1.53
     piling
    1.52
    yssey
    1.52
     sprawling
    1.50
    Activations Density 0.005%

    No Known Activations