© 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 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. 7592
    Prev
    Next
    INDEX
    Explanations

    references to proportions or fractions

    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
    1:0.02
    2:0.10
    3:0.25
    4:0.01
    5:0.03
    6:0.09
    7:0.04
    8:0.03
    9:0.08
    10:0.07
    11:0.22
    Negative Logits
    virt
    -1.40
    の�
    -1.22
    ロ
    -1.21
    tumblr
    -1.17
    ーティ
    -1.15
    imeo
    -1.14
    テ
    -1.12
    き
    -1.11
    RAW
    -1.08
    MT
    -1.07
    POSITIVE LOGITS
     squared
    1.26
     anymore
    1.24
    abyte
    1.16
     commuting
    1.14
     apprehens
    1.10
    assium
    1.09
     nor
    1.09
     allotted
    1.06
     hindsight
    1.04
     pie
    1.04
    Activations Density 0.004%

    No Known Activations