© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 8102
    Prev
    Next
    INDEX
    Explanations

    expressions of contrast or continuation in narratives

    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
    0:0.01
    1:0.05
    2:0.09
    3:0.07
    4:0.02
    5:0.04
    6:0.10
    7:0.07
    8:0.07
    9:0.18
    10:0.09
    11:0.16
    Negative Logits
    aroo
    -1.23
    anca
    -1.22
    HAM
    -1.21
    arez
    -1.11
    �
    -1.11
    anamo
    -1.07
    ITED
    -1.04
    Aren
    -1.03
    ullivan
    -1.02
    ROR
    -1.01
    POSITIVE LOGITS
    xual
    1.27
     technically
    1.17
     coerc
    1.11
     unavoid
    1.06
    aceous
    1.05
    luster
    1.05
     retains
    1.05
     advances
    1.05
     persists
    1.03
     adhere
    1.02
    Activations Density 0.009%

    No Known Activations