© 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. 11983
    Prev
    Next
    INDEX
    Explanations

    text related to political discussions and negotiations

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

    words and phrases related to communication and dialogue

    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
    2:0.17
    3:0.08
    4:0.01
    5:0.02
    6:0.05
    7:0.26
    8:0.14
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
    IUM
    -1.12
    EMP
    -1.04
     Shad
    -1.01
    VALUE
    -0.96
     Gib
    -0.94
     Weston
    -0.93
    emp
    -0.90
    ubi
    -0.90
    bath
    -0.87
     Rocks
    -0.86
    POSITIVE LOGITS
     motions
    1.25
    ython
    1.18
     transformations
    1.15
     mechanisms
    1.15
    ricular
    1.14
     routines
    1.11
     Flavoring
    1.09
     ACTIONS
    1.07
     procedures
    1.03
    ruary
    0.97
    Activations Density 0.056%

    No Known Activations