© 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. 5-ATT-KK
    11. 41906
    Prev
    Next
    INDEX
    Explanations

    temporal references related to the duration of experiences or events

    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
    0:0.01
    1:0.01
    2:0.16
    3:0.05
    4:0.14
    5:0.02
    6:0.07
    7:0.35
    8:0.03
    9:0.02
    10:0.04
    11:0.04
    Negative Logits
    imilar
    -1.80
    ��
    -1.61
    ��
    -1.53
    ��
    -1.49
    othy
    -1.49
    VS
    -1.47
     scatter
    -1.47
     welcome
    -1.45
    apter
    -1.42
    apest
    -1.42
    POSITIVE LOGITS
    duration
    1.94
     expires
    1.80
     eternity
    1.80
     adolesc
    1.72
     tenure
    1.62
     stint
    1.60
    pleted
    1.57
    eday
    1.56
     periods
    1.52
     Lent
    1.49
    Activations Density 0.008%

    No Known Activations