© 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. 2-ATT-KK
    11. 22132
    Prev
    Next
    INDEX
    Explanations

    terminology related to overnight events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.17
    3:0.09
    4:0.08
    5:0.09
    6:0.04
    7:0.03
    8:0.11
    9:0.17
    10:0.05
    11:0.02
    Negative Logits
    album
    -1.45
    worn
    -1.14
    existent
    -1.09
    podcast
    -1.08
    itely
    -1.08
    ogg
    -1.06
    ּ
    -1.06
    oof
    -1.05
    ALSE
    -1.05
    phe
    -1.04
    POSITIVE LOGITS
     ende
    1.40
     lockdown
    1.32
     commute
    1.32
     streng
    1.30
    cot
    1.16
     awoken
    1.16
    wake
    1.12
     livest
    1.08
     commuting
    1.06
     advis
    1.05
    Activations Density 0.006%

    No Known Activations