© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 5289
    Prev
    Next
    INDEX
    Explanations

    references to time spans and historical contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    references to time and historical context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    temporal references and expressions of time

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.09
    3:0.09
    4:0.02
    5:0.07
    6:0.11
    7:0.16
    8:0.06
    9:0.04
    10:0.11
    11:0.14
    Negative Logits
     referral
    -1.31
     announcements
    -1.24
     referrals
    -1.23
    itas
    -1.16
     affiliate
    -1.08
     scheduling
    -1.06
    Brow
    -1.03
     requests
    -1.01
     buttons
    -0.99
     solicit
    -0.99
    POSITIVE LOGITS
     reconstructed
    1.23
     descendant
    1.23
     suff
    1.14
    quartered
    1.14
     preserved
    1.13
    ouched
    1.12
     robber
    1.11
     regenerate
    1.11
     vanishing
    1.11
    idable
    1.11
    Activations Density 0.036%

    No Known Activations