© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 23255
    Prev
    Next
    INDEX
    Explanations

    statistics and historical events or contexts

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

    instances of the phrase "wave of" followed by a description of social or political movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.01
    2:0.22
    3:0.05
    4:0.29
    5:0.04
    6:0.02
    7:0.02
    8:0.04
    9:0.15
    10:0.04
    11:0.03
    Negative Logits
    SourceFile
    -1.53
    チ
    -1.38
    モ
    -1.36
    ▬
    -1.33
    Values
    -1.32
    作
    -1.31
    ーティ
    -1.31
    �士
    -1.27
     Dominion
    -1.26
    スト
    -1.24
    POSITIVE LOGITS
     flames
    1.49
     tears
    1.41
    rils
    1.38
    bia
    1.38
     haze
    1.36
    adesh
    1.33
     colours
    1.31
    visor
    1.28
     lockdown
    1.28
     agitation
    1.27
    Activations Density 0.003%

    No Known Activations