© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 470
    Prev
    Next
    INDEX
    Explanations

    timestamps and time-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.03
    3:0.07
    4:0.03
    5:0.08
    6:0.05
    7:0.30
    8:0.08
    9:0.03
    10:0.16
    11:0.03
    Negative Logits
     Knot
    -2.43
     November
    -2.40
     Bore
    -2.37
     ­
    -2.32
     September
    -2.27
    EMBER
    -2.25
     December
    -2.21
     Catalan
    -2.18
     July
    -2.18
     Brazilian
    -2.17
    POSITIVE LOGITS
    chwitz
    2.58
    ventures
    2.54
     exits
    2.49
    illation
    2.48
    anasia
    2.48
    isu
    2.43
    rium
    2.42
    heid
    2.37
    timer
    2.35
    zee
    2.35
    Activations Density 0.006%

    No Known Activations