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

    Neuronpedia

    Jacobian LensNEW
    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. 12456
    Prev
    Next
    INDEX
    Explanations

    specific points in time or temporal references within a narrative

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    temporal phrases and references to time

    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
    0:0.02
    1:0.03
    2:0.07
    3:0.06
    4:0.02
    5:0.04
    6:0.08
    7:0.05
    8:0.05
    9:0.34
    10:0.05
    11:0.15
    Negative Logits
     irre
    -1.23
    iger
    -1.21
     CODE
    -1.20
    osponsors
    -1.16
     permissions
    -1.11
     sponsor
    -1.09
     someday
    -1.09
     outstanding
    -1.08
     depend
    -1.07
    arcity
    -1.06
    POSITIVE LOGITS
    breaks
    1.47
    Stretch
    1.32
    slaught
    1.31
    due
    1.27
     Rampage
    1.26
    noon
    1.24
    assembly
    1.24
    panic
    1.22
     Ambro
    1.22
    Whe
    1.21
    Activations Density 0.020%

    No Known Activations