© 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. 3-ATT-KK
    11. 9264
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or guidance

    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
    0:0.02
    1:0.08
    2:0.10
    3:0.04
    4:0.01
    5:0.06
    6:0.07
    7:0.10
    8:0.14
    9:0.10
    10:0.12
    11:0.10
    Negative Logits
    putable
    -0.98
    ihara
    -0.97
    udicrous
    -0.97
    ′
    -0.95
     Gamble
    -0.90
    cised
    -0.87
    outheast
    -0.86
    ilated
    -0.86
    rapnel
    -0.84
    grand
    -0.84
    POSITIVE LOGITS
     Vera
    1.00
     Without
    1.00
     Otherwise
    0.99
     Normally
    0.94
    スト
    0.94
     Lent
    0.92
     ###
    0.90
    stals
    0.88
     Depending
    0.87
    letters
    0.86
    Activations Density 0.105%

    No Known Activations