© 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. 4647
    Prev
    Next
    INDEX
    Explanations

    references to URLs and links in the text

    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
    0:0.09
    1:0.02
    2:0.03
    3:0.13
    4:0.09
    5:0.04
    6:0.03
    7:0.11
    8:0.03
    9:0.01
    10:0.30
    11:0.06
    Negative Logits
     altogether
    -2.17
     Ung
    -1.89
     rookie
    -1.84
     sprang
    -1.80
     Blaster
    -1.77
     entirely
    -1.75
     Kard
    -1.75
     spont
    -1.75
     autonomy
    -1.75
     retali
    -1.72
    POSITIVE LOGITS
    yrinth
    2.85
    /?
    2.81
    /,
    2.78
    tips
    2.72
    /.
    2.72
    detail
    2.65
    ebin
    2.61
    forums
    2.43
    php
    2.38
    /)
    2.34
    Activations Density 0.029%

    No Known Activations