© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 5579
    Prev
    Next
    INDEX
    Explanations

    references to time periods and spans, focusing on years, days, months, and generations

    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
    0:0.04
    1:0.08
    2:0.19
    3:0.04
    4:0.04
    5:0.10
    6:0.08
    7:0.02
    8:0.22
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
    sth
    -1.88
    Fu
    -1.79
    wan
    -1.75
    ullivan
    -1.72
    affe
    -1.71
    Joy
    -1.69
    olin
    -1.69
    �
    -1.68
    Var
    -1.66
    anas
    -1.65
    POSITIVE LOGITS
     devoted
    1.90
    thodox
    1.69
     headlined
    1.68
     incarcerated
    1.65
     hanged
    1.58
     ripe
    1.56
     dedicated
    1.56
     begging
    1.55
     adolesc
    1.55
     transsexual
    1.51
    Activations Density 0.001%

    No Known Activations