© 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. 5224
    Prev
    Next
    INDEX
    Explanations

    elements related to email addresses and subscription processes

    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
    0:0.12
    1:0.02
    2:0.02
    3:0.06
    4:0.33
    5:0.11
    6:0.06
    7:0.09
    8:0.04
    9:0.01
    10:0.07
    11:0.02
    Negative Logits
     subsid
    -2.35
     spectator
    -2.32
     STATS
    -2.31
     crowdfunding
    -2.27
     crowds
    -2.25
     spectators
    -2.19
     masc
    -2.12
     commemor
    -2.06
     telev
    -2.06
    =>
    -2.03
    POSITIVE LOGITS
    hene
    2.54
     UNCLASSIFIED
    2.53
    eday
    2.44
    oyd
    2.39
    thren
    2.36
    inges
    2.35
    rils
    2.34
     Xie
    2.32
    ]+
    2.25
    enes
    2.22
    Activations Density 0.016%

    No Known Activations