© 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. 13741
    Prev
    Next
    INDEX
    Explanations

    examples of how something exemplifies a quality or concept

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

    instances of the word "exemplify" and its variants concerning various subjects or themes

    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
    0:0.01
    1:0.03
    2:0.08
    3:0.09
    4:0.02
    5:0.05
    6:0.06
    7:0.09
    8:0.11
    9:0.18
    10:0.07
    11:0.16
    Negative Logits
     investigates
    -1.16
     publishes
    -1.12
    enson
    -1.10
    OSED
    -1.08
     spor
    -1.03
     papers
    -1.03
     alerted
    -1.01
     weekends
    -1.00
     bog
    -1.00
    rade
    -0.94
    POSITIVE LOGITS
     archetype
    1.35
     embodiment
    1.25
    cellence
    1.24
     symbolism
    1.23
    universal
    1.22
    onomy
    1.21
     likeness
    1.21
     metaphor
    1.19
     quint
    1.17
    ortment
    1.14
    Activations Density 0.008%

    No Known Activations