© 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. 584
    Prev
    Next
    INDEX
    Explanations

    statements about logical reasoning and conclusions derived from analysis

    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
    0:0.43
    1:0.02
    2:0.17
    3:0.05
    4:0.02
    5:0.04
    6:0.02
    7:0.03
    8:0.02
    9:0.01
    10:0.11
    11:0.03
    Negative Logits
     Cele
    -2.29
    enegger
    -2.26
     servicing
    -2.25
     serv
    -2.25
     Advertisement
    -2.24
    Campaign
    -2.19
    campaign
    -2.17
    endor
    -2.15
     commercials
    -2.15
    gallery
    -2.09
    POSITIVE LOGITS
     conclusions
    4.07
     extrap
    3.37
     conclusion
    3.28
    Reviewed
    3.25
     IPCC
    2.63
     conjecture
    2.47
     intu
    2.42
    escap
    2.33
     formulated
    2.32
     confir
    2.28
    Activations Density 0.014%

    No Known Activations