© 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. 6515
    Prev
    Next
    INDEX
    Explanations

    numerical values that likely represent times or schedules

    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
    0:0.05
    1:0.03
    2:0.14
    3:0.08
    4:0.06
    5:0.03
    6:0.08
    7:0.08
    8:0.12
    9:0.12
    10:0.10
    11:0.05
    Negative Logits
    foundland
    -1.06
     vanished
    -1.00
     puzzle
    -0.99
    izoph
    -0.97
     yours
    -0.96
     melted
    -0.96
     evolution
    -0.93
     eaten
    -0.92
     literature
    -0.92
     Swed
    -0.91
    POSITIVE LOGITS
     intersections
    1.53
     apiece
    1.45
     checkpoints
    1.41
    CCC
    1.30
     intervals
    1.27
    Oracle
    1.25
    ertodd
    1.25
    mop
    1.25
     behest
    1.22
    ESPN
    1.21
    Activations Density 0.033%

    No Known Activations