© 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. 21549
    Prev
    Next
    INDEX
    Explanations

    references to educational standards and policies, particularly the Common Core and associated debates

    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
    0:0.04
    1:0.03
    2:0.26
    3:0.07
    4:0.15
    5:0.06
    6:0.04
    7:0.04
    8:0.07
    9:0.09
    10:0.07
    11:0.03
    Negative Logits
    ��
    -1.57
    hap
    -1.38
    eah
    -1.36
    eki
    -1.35
     Mehran
    -1.34
    ngth
    -1.29
    etsk
    -1.28
    sync
    -1.27
    \/\/
    -1.25
    ipl
    -1.24
    POSITIVE LOGITS
     Speech
    1.35
    ム
    1.31
    Application
    1.26
    Ground
    1.24
    ensical
    1.20
    SpaceEngineers
    1.19
    Demand
    1.19
     Initiative
    1.19
     Veterinary
    1.18
     Ground
    1.18
    Activations Density 0.004%

    No Known Activations