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. 44187
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance of specific facts or issues

    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
    0:0.01
    1:0.02
    2:0.06
    3:0.07
    4:0.09
    5:0.02
    6:0.19
    7:0.30
    8:0.03
    9:0.03
    10:0.04
    11:0.09
    Negative Logits
    20439
    -1.73
    erate
    -1.47
     muse
    -1.42
    erest
    -1.39
     CHRIST
    -1.31
    gged
    -1.26
     dearly
    -1.21
    uay
    -1.21
     wisely
    -1.18
    =-=-=-=-
    -1.17
    POSITIVE LOGITS
    Missing
    1.47
    ottesville
    1.43
     incap
    1.34
    today
    1.33
     Armory
    1.33
    celona
    1.31
    inctions
    1.28
     presence
    1.27
     residency
    1.27
     captivity
    1.26
    Activations Density 0.005%

    No Known Activations