© 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. 7213
    Prev
    Next
    INDEX
    Explanations

    terms related to revolutions and revolutionary movements

    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
    1:0.04
    2:0.04
    3:0.05
    4:0.06
    5:0.05
    6:0.10
    7:0.07
    8:0.04
    9:0.06
    10:0.11
    11:0.04
    Negative Logits
    othy
    -1.66
    ately
    -1.59
    機
    -1.53
    leted
    -1.38
     ware
    -1.31
    utical
    -1.30
    SourceFile
    -1.28
     packaged
    -1.27
     assessed
    -1.26
    oufl
    -1.25
    POSITIVE LOGITS
    asis
    1.65
    dinand
    1.59
     Judgment
    1.50
    din
    1.50
     Sabb
    1.42
    zinski
    1.40
    ismo
    1.39
    ebus
    1.38
     Socialist
    1.36
    hani
    1.35
    Activations Density 0.004%

    No Known Activations