© 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. 10-ATT-KK
    11. 7988
    Prev
    Next
    INDEX
    Explanations

    references to legislative and regulatory processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.15
    3:0.16
    4:0.14
    5:0.11
    6:0.06
    7:0.07
    8:0.03
    9:0.06
    10:0.05
    11:0.05
    Negative Logits
     humour
    -3.68
     brill
    -3.62
     civilisation
    -3.56
    colour
    -3.56
     rumours
    -3.40
     flavour
    -3.31
     rubbish
    -3.26
     flavours
    -3.26
     organise
    -3.18
     colourful
    -3.08
    POSITIVE LOGITS
    �
    6.04
     �
    5.25
    �
    4.48
    †
    4.33
    ►
    4.25
    ­
    3.95
    §
    3.92
    �
    3.85
    ADVERTISEMENT
    3.75
    ‎
    3.74
    Activations Density 1.367%

    No Known Activations