© 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. 14143
    Prev
    Next
    INDEX
    Explanations

    text related to coding, specifically focusing on roles and modules within a system

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    programming-related keywords and function definitions

    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
    0:0.28
    1:0.06
    2:0.04
    3:0.03
    4:0.15
    5:0.06
    6:0.08
    7:0.07
    8:0.06
    9:0.02
    10:0.07
    11:0.03
    Negative Logits
    ���
    -1.89
     Canaver
    -1.67
     サーティワン
    -1.55
     referen
    -1.41
    ;;;;;;;;;;;;
    -1.36
     Parad
    -1.34
     synerg
    -1.32
     facult
    -1.31
    paralle
    -1.31
    ーティ
    -1.28
    POSITIVE LOGITS
    Sent
    1.41
    Tex
    1.39
    rod
    1.34
    tis
    1.33
    Lair
    1.33
    nor
    1.32
    rower
    1.31
    Card
    1.30
    nil
    1.30
    Sam
    1.28
    Activations Density 0.046%

    No Known Activations