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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 6799
    Prev
    Next
    INDEX
    Explanations

    phrases highlighting the world's most significant statistics or rankings related to various subjects

    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
    0:0.02
    1:0.02
    2:0.06
    3:0.04
    4:0.01
    5:0.05
    6:0.47
    7:0.10
    8:0.03
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
    tesy
    -1.42
    tein
    -1.41
    utsu
    -1.34
    xtap
    -1.33
     caut
    -1.32
    ooters
    -1.23
    :[
    -1.21
    opsis
    -1.20
    ��
    -1.20
    boa
    -1.19
    POSITIVE LOGITS
     Consortium
    1.50
     Summit
    1.28
    heid
    1.24
     Colomb
    1.24
    istani
    1.22
     Glob
    1.22
     Arab
    1.21
     Babel
    1.20
     Columb
    1.20
     Tire
    1.20
    Activations Density 0.141%

    No Known Activations