© 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. 2-ATT-KK
    11. 14675
    Prev
    Next
    INDEX
    Explanations

    questions and invitations in dialogues between individuals where one party is directing the conversation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.01
    2:0.23
    3:0.05
    4:0.07
    5:0.07
    6:0.02
    7:0.01
    8:0.29
    9:0.07
    10:0.04
    11:0.02
    Negative Logits
    olate
    -1.36
    inction
    -1.35
    vironment
    -1.20
    entary
    -1.11
     NETWORK
    -1.09
     Pipeline
    -1.08
    mire
    -1.06
    ept
    -1.06
     Swim
    -1.05
    paces
    -1.04
    POSITIVE LOGITS
     forgiveness
    1.31
    Scot
    1.18
    question
    1.17
    Newsletter
    1.17
     critics
    1.15
    odan
    1.11
     parting
    1.11
    Response
    1.11
    SEE
    1.10
    Critics
    1.08
    Activations Density 0.041%

    No Known Activations