© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 14374
    Prev
    Next
    INDEX
    Explanations

    commands and instructions related to setting up various software environments

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    installation commands and package management terms related to software

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.06
    1:0.10
    2:0.10
    3:0.04
    4:0.05
    5:0.07
    6:0.07
    7:0.09
    8:0.14
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
    田
    -1.39
    cffffcc
    -1.30
    ccording
    -1.17
     Perspective
    -1.15
    ixties
    -1.15
    imester
    -1.10
    olitics
    -1.09
    alogue
    -1.07
    opathy
    -1.06
    olitical
    -1.05
    POSITIVE LOGITS
    orage
    1.22
    jen
    1.20
    Cache
    1.19
    bott
    1.17
    ware
    1.16
    db
    1.15
    bg
    1.15
    tu
    1.13
    cache
    1.07
    info
    1.07
    Activations Density 0.022%

    No Known Activations