© 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. 12187
    Prev
    Next
    INDEX
    Explanations

    references to legacy and historical impact across various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to legacy and historical significance

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    1:0.02
    2:0.05
    3:0.18
    4:0.01
    5:0.03
    6:0.07
    7:0.19
    8:0.04
    9:0.06
    10:0.07
    11:0.20
    Negative Logits
    etsk
    -1.44
    kov
    -1.32
    pport
    -1.31
    upt
    -1.30
    jab
    -1.27
    hots
    -1.26
    reply
    -1.22
    Nusra
    -1.21
     sidx
    -1.19
    otaur
    -1.17
    POSITIVE LOGITS
     legacy
    1.43
     generations
    1.40
    artifacts
    1.34
     Ashes
    1.17
     Generations
    1.13
     relics
    1.11
     Memories
    1.11
     Diseases
    1.11
     inherited
    1.10
     relic
    1.10
    Activations Density 0.010%

    No Known Activations