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. 7197
    Prev
    Next
    INDEX
    Explanations

    gerunds and participles associated with subtle emotional or relational dynamics

    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
    0:0.02
    1:0.02
    2:0.03
    3:0.05
    4:0.12
    5:0.03
    6:0.05
    7:0.42
    8:0.04
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
     handc
    -1.69
    urtles
    -1.54
     scramble
    -1.52
     trending
    -1.52
     zipper
    -1.51
    radio
    -1.51
    oto
    -1.50
    hid
    -1.50
    tera
    -1.48
     TRANS
    -1.47
    POSITIVE LOGITS
     generously
    1.82
     Benefit
    1.75
     praise
    1.69
     gifts
    1.60
    urances
    1.57
     occas
    1.54
     kindness
    1.48
    ributes
    1.48
     colle
    1.47
     plent
    1.46
    Activations Density 0.001%

    No Known Activations