© 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. 13752
    Prev
    Next
    INDEX
    Explanations

    software-related terms and concepts, such as specific software functionalities and technologies

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

    terms related to software functionality and usability

    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
    0:0.03
    1:0.04
    2:0.05
    3:0.05
    4:0.03
    5:0.07
    6:0.09
    7:0.35
    8:0.06
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
    pez
    -1.39
    の�
    -1.30
    zl
    -1.23
    jri
    -1.22
    bernatorial
    -1.22
     dign
    -1.21
    deen
    -1.20
    omore
    -1.18
    ğ
    -1.18
    EXP
    -1.14
    POSITIVE LOGITS
    enhagen
    1.36
     interfaces
    1.35
     software
    1.32
    properties
    1.25
     databases
    1.24
     Arduino
    1.23
    software
    1.22
     upload
    1.18
     Models
    1.18
     controls
    1.17
    Activations Density 0.022%

    No Known Activations