© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-ATT-KK
    11. 23441
    Prev
    Next
    INDEX
    Explanations

    references to significant political events or contexts

    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
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.07
    5:0.09
    6:0.07
    7:0.06
    8:0.08
    9:0.09
    10:0.08
    11:0.09
    Negative Logits
    ................................................................
    -1.48
     GOODMAN
    -1.47
    raft
    -1.45
    DragonMagazine
    -1.44
    FAQ
    -1.40
    Hello
    -1.33
     foreskin
    -1.30
     Medline
    -1.29
    ippi
    -1.25
     Osw
    -1.23
    POSITIVE LOGITS
    venge
    1.58
     exting
    1.30
    vre
    1.26
    bent
    1.24
     subordinates
    1.23
    existent
    1.23
    ield
    1.22
    arent
    1.19
    achable
    1.19
    bol
    1.15
    Activations Density 0.000%

    No Known Activations