© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28584
    Prev
    Next
    INDEX
    Explanations

    the letter "t" in various contexts

    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
    0:0.08
    1:0.08
    2:0.08
    3:0.07
    4:0.08
    5:0.08
    6:0.11
    7:0.09
    8:0.07
    9:0.07
    10:0.06
    11:0.07
    Negative Logits
     mete
    -1.94
    peat
    -1.75
    recy
    -1.67
     rewards
    -1.52
    Leaks
    -1.49
     fences
    -1.46
    paying
    -1.45
     pet
    -1.44
     carpet
    -1.42
     Showtime
    -1.40
    POSITIVE LOGITS
     Emin
    1.57
     Isles
    1.56
     Leilan
    1.56
    esm
    1.53
     Cran
    1.51
     Sail
    1.50
     Firstly
    1.50
    achus
    1.48
     Entered
    1.47
    ople
    1.46
    Activations Density 0.000%

    No Known Activations