© 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. 6886
    Prev
    Next
    INDEX
    Explanations

    references to email and invalid email addresses

    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
    1:0.09
    2:0.08
    3:0.09
    4:0.02
    5:0.05
    6:0.10
    7:0.14
    8:0.06
    9:0.12
    10:0.07
    11:0.10
    Negative Logits
    natureconservancy
    -1.23
    amorph
    -1.18
     uninterrupted
    -1.04
    shift
    -1.02
    rounded
    -1.02
    ardless
    -1.00
    ooth
    -1.00
    unin
    -0.96
    STDOUT
    -0.96
    ivable
    -0.95
    POSITIVE LOGITS
     apologised
    1.13
    POSE
    1.02
    miah
    0.97
     Cu
    0.96
    Cu
    0.93
    QL
    0.92
     guiActiveUnfocused
    0.92
    ��
    0.92
    ENT
    0.92
     Midlands
    0.92
    Activations Density 0.001%

    No Known Activations