Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 7282
    Prev
    Next
    INDEX
    Explanations

    instances of the past tense verb "ed" and its use in specific 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
    0:0.03
    1:0.01
    2:0.08
    3:0.08
    4:0.18
    5:0.04
    6:0.04
    7:0.28
    8:0.04
    9:0.04
    10:0.05
    11:0.07
    Negative Logits
    itsch
    -1.66
    icrobial
    -1.61
    lav
    -1.52
    apons
    -1.51
    utsu
    -1.48
    tan
    -1.48
     conserve
    -1.48
    omial
    -1.47
    ongevity
    -1.45
    allery
    -1.43
    POSITIVE LOGITS
     wiser
    1.60
     Luxem
    1.56
    LEASE
    1.51
    OUND
    1.50
     unlaw
    1.45
     Doodle
    1.42
     cracks
    1.40
     Egyptians
    1.37
     deaf
    1.35
    Companies
    1.34
    Activations Density 0.000%

    No Known Activations