© 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. 10-ATT-KK
    11. 8994
    Prev
    Next
    INDEX
    Explanations

    references to time, particularly concerning durations and changes over months and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    3:0.04
    4:0.05
    5:0.22
    6:0.01
    7:0.03
    8:0.01
    9:0.45
    10:0.01
    11:0.03
    Negative Logits
    pired
    -2.29
    PLIED
    -2.13
     checked
    -2.09
    printed
    -2.07
    rolled
    -2.04
     engraved
    -2.02
    rets
    -2.01
     Wanted
    -1.98
     guiActiveUnfocused
    -1.98
    THING
    -1.98
    POSITIVE LOGITS
    orically
    2.95
     owing
    2.92
     due
    2.92
     considerably
    2.81
     markedly
    2.79
     exponentially
    2.78
     rapidly
    2.73
    lator
    2.64
     Since
    2.62
    since
    2.60
    Activations Density 0.186%

    No Known Activations