© 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. 1085
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in the text

    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
    0:0.16
    1:0.24
    2:0.03
    3:0.02
    4:0.02
    5:0.21
    6:0.06
    7:0.01
    8:0.03
    9:0.09
    10:0.04
    11:0.03
    Negative Logits
    py
    -2.15
    20439
    -2.13
    horn
    -1.81
    hap
    -1.81
    pak
    -1.77
    kus
    -1.67
    tis
    -1.66
    Pand
    -1.64
    pe
    -1.64
    lad
    -1.61
    POSITIVE LOGITS
    .?
    1.66
    cember
    1.59
    ommel
    1.59
     etiquette
    1.58
     simultane
    1.57
     dates
    1.55
     Rowe
    1.51
     consecut
    1.50
     Saud
    1.49
    ruary
    1.49
    Activations Density 0.002%

    No Known Activations