© 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. 3-ATT-KK
    11. 11426
    Prev
    Next
    INDEX
    Explanations

    mentions and references within a text, particularly focusing on preceding phrases or contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.03
    2:0.05
    3:0.27
    4:0.01
    5:0.03
    6:0.04
    7:0.20
    8:0.07
    9:0.11
    10:0.06
    11:0.08
    Negative Logits
     Tycoon
    -1.38
    ierre
    -1.34
    thia
    -1.34
    efficients
    -1.31
    velt
    -1.27
    ruce
    -1.25
    wagen
    -1.23
    inois
    -1.21
    robe
    -1.18
    enhagen
    -1.15
    POSITIVE LOGITS
     phrases
    1.27
     facts
    1.17
     Oval
    1.15
     Khan
    1.14
     juven
    1.13
    XM
    1.13
    ��
    1.12
     inciting
    1.11
     pregnant
    1.09
     homosexuality
    1.05
    Activations Density 0.006%

    No Known Activations