© 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. 34427
    Prev
    Next
    INDEX
    Explanations

    references to returning or restoring items or concepts

    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
    2:0.09
    3:0.09
    4:0.26
    5:0.02
    6:0.04
    7:0.28
    8:0.02
    9:0.02
    10:0.05
    11:0.04
    Negative Logits
    artment
    -1.99
    panel
    -1.92
    quartered
    -1.91
    Desk
    -1.91
    ategories
    -1.84
    swer
    -1.78
    inery
    -1.77
    PLIED
    -1.74
    autions
    -1.72
    iannopoulos
    -1.69
    POSITIVE LOGITS
     memories
    2.35
     rejuven
    1.83
     nostalgia
    1.79
     sanity
    1.79
     scapego
    1.79
     morale
    1.78
     vengeance
    1.71
     continuity
    1.68
     polio
    1.67
     immortality
    1.64
    Activations Density 0.009%

    No Known Activations