© 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. 17874
    Prev
    Next
    INDEX
    Explanations

    subjective opinions and comparisons related to experiences, particularly in regard to evaluations of quality or preference

    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
    0:0.08
    1:0.03
    2:0.07
    3:0.17
    4:0.04
    5:0.07
    6:0.03
    7:0.09
    8:0.03
    9:0.02
    10:0.31
    11:0.02
    Negative Logits
     externalToEVAOnly
    -2.31
    enegger
    -2.01
     offices
    -1.97
     workplace
    -1.94
     workplaces
    -1.90
    iage
    -1.89
     BUS
    -1.87
     eras
    -1.87
     storefront
    -1.80
     businesses
    -1.78
    POSITIVE LOGITS
    most
    2.46
    mostly
    2.42
     Mostly
    2.35
     consisted
    2.32
    hest
    2.28
    liest
    2.26
     least
    2.16
     chiefly
    2.15
     outwe
    2.13
    few
    2.11
    Activations Density 0.041%

    No Known Activations