© 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. 5295
    Prev
    Next
    INDEX
    Explanations

    action-oriented verbs related to personal initiatives or social engagement

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

    verbs indicating actions associated with personal desires or societal issues

    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
    0:0.04
    1:0.05
    2:0.14
    3:0.03
    4:0.02
    5:0.04
    6:0.07
    7:0.10
    8:0.13
    9:0.17
    10:0.09
    11:0.07
    Negative Logits
     aided
    -1.35
     occ
    -1.18
     resur
    -1.18
     spawned
    -1.11
     counting
    -1.08
     registers
    -1.06
     tides
    -1.05
     littered
    -1.04
     guiActiveUn
    -1.04
     numbered
    -1.00
    POSITIVE LOGITS
     ASAP
    1.31
     someday
    1.29
    uate
    1.22
     idols
    1.13
    ipedia
    1.13
    anything
    1.11
     tomorrow
    1.09
     future
    1.08
    itutes
    1.07
    irie
    1.07
    Activations Density 0.090%

    No Known Activations