© 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. 15142
    Prev
    Next
    INDEX
    Explanations

    the end of text markers and technical text related to computer hardware or software

    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
    0:0.10
    1:0.02
    2:0.11
    3:0.11
    4:0.06
    5:0.17
    6:0.04
    7:0.02
    8:0.12
    9:0.10
    10:0.07
    11:0.04
    Negative Logits
    mble
    -1.38
    ariat
    -1.28
    earances
    -1.25
    istries
    -1.22
    orship
    -1.16
    osterone
    -1.14
     suffice
    -1.10
    forts
    -1.07
    itars
    -1.07
    lation
    -1.06
    POSITIVE LOGITS
    rats
    1.02
    reating
    1.00
    usual
    0.97
     Continuous
    0.96
     Tile
    0.95
    pol
    0.95
    rows
    0.95
     orig
    0.94
     Root
    0.93
     Researchers
    0.92
    Activations Density 0.024%

    No Known Activations