© 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. 21512
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate actions related to searching, querying, and financial transactions

    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
    1:0.03
    2:0.15
    3:0.06
    4:0.27
    5:0.07
    6:0.03
    7:0.02
    8:0.10
    9:0.06
    10:0.06
    11:0.03
    Negative Logits
    hat
    -1.38
    Lenin
    -1.38
    rants
    -1.34
    warts
    -1.33
     Hik
    -1.30
    arts
    -1.29
     Britann
    -1.22
     favored
    -1.21
    bush
    -1.20
    機
    -1.19
    POSITIVE LOGITS
    uate
    1.85
     safely
    1.82
    ANY
    1.50
    byter
    1.41
    eger
    1.40
     improv
    1.38
     cheaply
    1.35
     anything
    1.33
     efficiently
    1.29
    ibly
    1.29
    Activations Density 0.042%

    No Known Activations