© 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. 5-ATT-KK
    11. 25976
    Prev
    Next
    INDEX
    Explanations

    instances of the word "t"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.07
    2:0.07
    3:0.08
    4:0.08
    5:0.07
    6:0.08
    7:0.11
    8:0.07
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
     interpreting
    -1.96
     wiser
    -1.89
     relational
    -1.83
     neural
    -1.76
     fashion
    -1.73
     biochemical
    -1.72
     fortunes
    -1.71
     telecommunications
    -1.71
     constitu
    -1.70
     publishing
    -1.69
    POSITIVE LOGITS
    ortium
    2.10
    apest
    2.07
    asted
    2.06
    RIP
    1.97
    drawn
    1.85
    uckles
    1.84
    raped
    1.81
    odore
    1.78
    cade
    1.77
    appropriately
    1.75
    Activations Density 0.000%

    No Known Activations