© 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 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. 12373
    Prev
    Next
    INDEX
    Explanations

    instances of people trying to find something or discovering something in different contexts

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

    the use of transitional phrases and actions in a narrative context

    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
    1:0.28
    2:0.07
    3:0.03
    4:0.01
    5:0.03
    6:0.13
    7:0.03
    8:0.07
    9:0.12
    10:0.04
    11:0.12
    Negative Logits
    hess
    -1.50
    rongh
    -1.33
    cision
    -1.25
    acas
    -1.20
    oplan
    -1.20
    cium
    -1.18
    ashington
    -1.16
    zik
    -1.13
    onomy
    -1.13
    oshenko
    -1.12
    POSITIVE LOGITS
    ADRA
    1.51
    FIN
    1.32
    ELY
    1.29
     reapp
    1.22
     caveats
    1.17
     anew
    1.16
    TPS
    1.16
    Ire
    1.14
     secondly
    1.13
    AIR
    1.11
    Activations Density 0.100%

    No Known Activations