© 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. 22525
    Prev
    Next
    INDEX
    Explanations

    words related to business negotiations, terms, and agreements

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

    phrases related to negotiation and terms of agreement

    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
    0:0.06
    1:0.03
    2:0.07
    3:0.06
    4:0.07
    5:0.06
    6:0.03
    7:0.03
    8:0.38
    9:0.08
    10:0.05
    11:0.03
    Negative Logits
    rendered
    -1.38
    oyal
    -1.27
    xtap
    -1.27
    ielding
    -1.27
     distinguished
    -1.26
     Access
    -1.26
     devoted
    -1.24
    ocation
    -1.22
     pretended
    -1.21
    Reviewed
    -1.20
    POSITIVE LOGITS
    zag
    1.51
    BuyableInstoreAndOnline
    1.40
     heals
    1.35
    DEM
    1.30
    ِ
    1.26
    Kal
    1.23
    details
    1.23
    bath
    1.22
    obin
    1.20
    andro
    1.20
    Activations Density 0.044%

    No Known Activations