© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 11335
    Prev
    Next
    INDEX
    Explanations

    frequency of official statements or announcements

    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
    1:0.05
    2:0.14
    3:0.03
    4:0.05
    5:0.07
    6:0.07
    7:0.07
    8:0.12
    9:0.12
    10:0.10
    11:0.09
    Negative Logits
    avorite
    -1.53
    Tags
    -1.24
    ensibly
    -1.24
    asons
    -1.18
    anners
    -1.17
    ouls
    -1.17
    rogens
    -1.16
    undown
    -1.15
    ramids
    -1.12
    ',"
    -1.11
    POSITIVE LOGITS
     Janeiro
    1.49
     context
    1.35
     midst
    1.25
     CNBC
    1.25
     behalf
    1.24
    ihar
    1.21
     nutshell
    1.18
    ibus
    1.18
    cca
    1.15
     guise
    1.15
    Activations Density 0.071%

    No Known Activations