© 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. 3320
    Prev
    Next
    INDEX
    Explanations

    dates and locations associated with events

    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
    0:0.09
    1:0.01
    2:0.03
    3:0.13
    4:0.03
    5:0.14
    6:0.02
    7:0.09
    8:0.04
    9:0.02
    10:0.31
    11:0.03
    Negative Logits
     tomorrow
    -2.76
     fortnight
    -2.51
     sooner
    -2.34
     soon
    -2.27
     tonight
    -2.27
     yesterday
    -2.14
     sometime
    -2.10
     shortly
    -1.95
     ASAP
    -1.92
     midday
    -1.89
    POSITIVE LOGITS
    tained
    2.12
    tain
    1.97
    pecially
    1.96
    isoft
    1.92
    ulhu
    1.91
    isu
    1.90
    ategor
    1.88
    qua
    1.81
    .''.
    1.80
    apons
    1.79
    Activations Density 0.026%

    No Known Activations