© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43497
    Prev
    Next
    INDEX
    Explanations

    specific years and significant dates within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    2:0.18
    3:0.04
    4:0.22
    5:0.03
    6:0.07
    7:0.03
    8:0.13
    9:0.05
    10:0.06
    11:0.07
    Negative Logits
    Reloaded
    -1.17
    �醒
    -1.16
    ffen
    -1.02
    Hung
    -0.97
    ��
    -0.95
    Motor
    -0.94
    FU
    -0.93
     undes
    -0.92
    ���
    -0.92
     *)
    -0.91
    POSITIVE LOGITS
     thereafter
    1.09
    versely
    1.08
    actly
    1.07
    quickShipAvailable
    1.05
    numbered
    1.02
    lisher
    1.00
     succeeding
    0.95
    ea
    0.95
     respectively
    0.95
    uki
    0.94
    Activations Density 0.070%

    No Known Activations