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. 7382
    Prev
    Next
    INDEX
    Explanations

    phrases indicating requests for more information

    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
    0:0.11
    1:0.25
    2:0.04
    3:0.05
    4:0.03
    5:0.11
    6:0.04
    7:0.03
    8:0.08
    9:0.07
    10:0.07
    11:0.07
    Negative Logits
    �
    -1.73
    ensional
    -1.54
    del
    -1.53
     Lam
    -1.52
    Ult
    -1.50
    -+-+
    -1.48
     latch
    -1.47
    ouble
    -1.47
     Bung
    -1.44
    orc
    -1.44
    POSITIVE LOGITS
    taboola
    1.72
    SPONSORED
    1.59
    reciation
    1.55
    udes
    1.54
    photo
    1.54
    licts
    1.52
    yright
    1.51
    =#
    1.48
     Citation
    1.46
    ItemTracker
    1.45
    Activations Density 0.001%

    No Known Activations