© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 7286
    Prev
    Next
    INDEX
    Explanations

    references to specific data sources and reporting methods used in scientific contexts

    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
    0:0.19
    1:0.04
    2:0.08
    3:0.16
    4:0.04
    5:0.08
    6:0.02
    7:0.08
    8:0.12
    9:0.02
    10:0.08
    11:0.03
    Negative Logits
    nen
    -2.34
     skating
    -2.31
     clauses
    -2.16
     skate
    -2.13
    geries
    -2.11
    steen
    -2.05
     bait
    -2.05
     boiler
    -1.99
     boards
    -1.96
     lett
    -1.95
    POSITIVE LOGITS
     Hubble
    2.98
     Observatory
    2.86
    NASA
    2.78
     Nasa
    2.68
     Flickr
    2.63
     telescope
    2.45
    Lens
    2.43
     NASA
    2.41
     Imaging
    2.37
     Moff
    2.34
    Activations Density 0.001%

    No Known Activations