© 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. 21166
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and aspiration

    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
    0:0.03
    1:0.01
    2:0.08
    3:0.09
    4:0.05
    5:0.02
    6:0.28
    7:0.17
    8:0.03
    9:0.02
    10:0.09
    11:0.07
    Negative Logits
     Syndrome
    -1.39
     syndrome
    -1.28
    heid
    -1.27
    sheet
    -1.24
     anatomy
    -1.16
     [-
    -1.15
    >>\
    -1.14
     dimensions
    -1.13
    worldly
    -1.11
     Falk
    -1.10
    POSITIVE LOGITS
     confir
    1.55
     tremend
    1.46
     destro
    1.36
    ivers
    1.34
    othe
    1.31
     toget
    1.29
     recreate
    1.29
    Catalog
    1.26
     nostalg
    1.26
     hoped
    1.25
    Activations Density 0.012%

    No Known Activations