© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 36711
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of explaining or clarifying concepts and phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.05
    3:0.13
    4:0.32
    5:0.02
    6:0.05
    7:0.15
    8:0.03
    9:0.05
    10:0.07
    11:0.07
    Negative Logits
    cknow
    -1.74
    ーク
    -1.64
    Static
    -1.58
     satell
    -1.52
    ryu
    -1.50
    antage
    -1.48
    shi
    -1.43
    orum
    -1.42
    龍
    -1.41
    Frameworks
    -1.40
    POSITIVE LOGITS
     dearly
    1.54
    )].
    1.45
     downfall
    1.45
     disproportionate
    1.41
     differently
    1.41
     favour
    1.39
     losses
    1.38
     Flavoring
    1.36
     [*
    1.36
     part
    1.35
    Activations Density 0.015%

    No Known Activations