© 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. 12205
    Prev
    Next
    INDEX
    Explanations

    dates and times in the text

    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
    0:0.18
    1:0.01
    2:0.03
    3:0.22
    4:0.04
    5:0.09
    6:0.02
    7:0.08
    8:0.05
    9:0.01
    10:0.18
    11:0.04
    Negative Logits
     purse
    -1.91
     whisk
    -1.89
     clout
    -1.84
     rehe
    -1.84
     dipping
    -1.83
     bribe
    -1.81
     payoff
    -1.81
     residual
    -1.78
     reluctance
    -1.77
     inclination
    -1.77
    POSITIVE LOGITS
     Discussion
    2.49
     Topics
    2.40
     Obst
    2.20
    WOR
    2.15
     Trees
    2.10
     Tags
    2.09
     Topic
    2.05
     Contents
    2.04
     Updates
    2.04
     Recommend
    2.02
    Activations Density 0.008%

    No Known Activations