© 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. 11116
    Prev
    Next
    INDEX
    Explanations

    references to scientific instruments and satellite data related to space exploration

    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
    0:0.23
    1:0.02
    2:0.14
    3:0.12
    4:0.06
    5:0.11
    6:0.03
    7:0.06
    8:0.06
    9:0.03
    10:0.07
    11:0.02
    Negative Logits
    iquette
    -2.49
     affirmative
    -2.38
    reprene
    -2.31
     Mortal
    -2.30
    ocrates
    -2.28
    agonist
    -2.21
    advertising
    -2.21
    ombies
    -2.20
    izophren
    -2.18
    ammy
    -2.16
    POSITIVE LOGITS
     telescopes
    3.69
     satellite
    3.60
     infrared
    3.57
     Observatory
    3.51
     Hubble
    3.47
     telescope
    3.47
     satellites
    3.40
     astronomers
    3.37
     orbiting
    3.28
     imaging
    3.21
    Activations Density 0.250%

    No Known Activations