© 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. 22686
    Prev
    Next
    INDEX
    Explanations

    technical terms or phrases used in various fields such as technology, health, law, and business

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

    phrases indicating inevitability or unavoidability

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.08
    1:0.03
    2:0.11
    3:0.11
    4:0.08
    5:0.07
    6:0.03
    7:0.03
    8:0.13
    9:0.20
    10:0.07
    11:0.02
    Negative Logits
    eters
    -1.24
    enture
    -1.20
    agall
    -1.16
    enged
    -1.15
    esses
    -1.10
    ificantly
    -1.04
    secut
    -1.04
    ished
    -1.04
    utra
    -1.02
    icer
    -1.02
    POSITIVE LOGITS
    PsyNetMessage
    1.21
     unforeseen
    1.16
    ドラ
    1.15
    ebted
    1.13
     outcome
    1.13
     outweigh
    1.13
    mony
    1.10
    rosso
    1.05
    lihood
    1.03
     Andersen
    1.03
    Activations Density 0.022%

    No Known Activations