© 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. 14989
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or specific settings

    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
    0:0.07
    1:0.01
    2:0.19
    3:0.07
    4:0.22
    5:0.07
    6:0.01
    7:0.01
    8:0.12
    9:0.12
    10:0.03
    11:0.01
    Negative Logits
    netflix
    -1.68
    nect
    -1.42
    raq
    -1.39
    QL
    -1.36
    eday
    -1.33
    amaz
    -1.30
    onne
    -1.30
    oir
    -1.30
    olkien
    -1.29
    oqu
    -1.27
    POSITIVE LOGITS
     bounds
    1.73
     confines
    1.55
     Territory
    1.54
     boundaries
    1.51
     restraints
    1.46
     Territories
    1.44
     scope
    1.34
     limits
    1.33
     coasts
    1.31
     borders
    1.31
    Activations Density 0.020%

    No Known Activations