© 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. 21440
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries related to systems, relationships, and other data-driven implications

    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
    0:0.07
    1:0.06
    2:0.06
    3:0.10
    4:0.08
    5:0.10
    6:0.16
    7:0.04
    8:0.08
    9:0.07
    10:0.09
    11:0.05
    Negative Logits
    interstitial
    -1.17
    furt
    -1.16
    Leod
    -1.12
    ��
    -1.12
     Reuters
    -1.11
     REUTERS
    -1.10
     parap
    -1.10
    enegger
    -1.10
    之
    -1.09
    �醒
    -1.08
    POSITIVE LOGITS
    FAQ
    1.19
    package
    1.19
     horm
    1.18
     nutshell
    1.16
    igslist
    1.15
    answered
    1.15
    ?:
    1.14
    reetings
    1.11
    ----
    1.11
    !!!!!!!!
    1.11
    Activations Density 0.162%

    No Known Activations