© 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. 545
    Prev
    Next
    INDEX
    Explanations

    requests and actions related to making a change or taking initiative

    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
    0:0.04
    1:0.02
    2:0.08
    3:0.26
    4:0.02
    5:0.08
    6:0.02
    7:0.04
    8:0.03
    9:0.02
    10:0.33
    11:0.02
    Negative Logits
     undet
    -2.63
     until
    -2.14
     underage
    -2.06
     uninterrupted
    -2.02
     lasts
    -2.00
    during
    -1.97
     unnoticed
    -1.93
     trapped
    -1.92
     untreated
    -1.92
     continuously
    -1.89
    POSITIVE LOGITS
     recons
    2.94
     reconsider
    2.69
     rethink
    2.66
     anew
    2.56
     rejo
    2.47
     rejoice
    2.36
     politic
    2.25
     rebirth
    2.18
    ocracy
    2.11
    ndum
    2.09
    Activations Density 0.039%

    No Known Activations