© 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. 3-ATT-KK
    11. 14145
    Prev
    Next
    INDEX
    Explanations

    words related to technical information and documentation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the conjunction "and" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.09
    3:0.08
    4:0.05
    5:0.03
    6:0.15
    7:0.12
    8:0.09
    9:0.07
    10:0.13
    11:0.08
    Negative Logits
    stice
    -1.15
     fame
    -1.11
    bath
    -1.04
     mansion
    -0.99
     Omaha
    -0.93
     Lamar
    -0.91
     boutique
    -0.91
     reunion
    -0.90
    clave
    -0.89
    elson
    -0.89
    POSITIVE LOGITS
    pecially
    1.26
     enthusi
    1.18
     eleph
    1.17
     skelet
    1.15
     tremend
    1.14
     acknow
    1.12
     volunte
    1.10
     obser
    1.09
    hovah
    1.09
     WARN
    1.08
    Activations Density 0.035%

    No Known Activations