© 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. 13502
    Prev
    Next
    INDEX
    Explanations

    technical terms related to typing and keyboards, along with some technical specifications

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

    attributes describing the quality and design of products, particularly focusing on durability, modularity, and compactness

    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
    1:0.03
    2:0.06
    3:0.12
    4:0.02
    5:0.06
    6:0.10
    7:0.21
    8:0.04
    9:0.03
    10:0.09
    11:0.16
    Negative Logits
    usra
    -1.30
    zar
    -1.14
    reon
    -1.13
     Behavioral
    -1.12
     Sina
    -1.11
     twitter
    -1.11
    xual
    -1.09
    ��
    -1.08
    HAEL
    -1.08
    Ask
    -1.05
    POSITIVE LOGITS
     srfAttach
    1.36
     modular
    1.31
     sturdy
    1.25
    Mini
    1.24
     durable
    1.22
     rugged
    1.18
     withstand
    1.15
    gear
    1.14
    angular
    1.13
     scalable
    1.13
    Activations Density 0.025%

    No Known Activations