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. 44388
    Prev
    Next
    INDEX
    Explanations

    references to age, particularly concerning children and familial relationships

    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
    0:0.03
    1:0.01
    2:0.05
    3:0.05
    4:0.04
    5:0.06
    6:0.04
    7:0.03
    8:0.04
    9:0.04
    10:0.46
    11:0.10
    Negative Logits
     capitals
    -1.84
     exclus
    -1.80
     fav
    -1.75
     marginal
    -1.67
     alliances
    -1.65
     opp
    -1.65
     commissions
    -1.65
     Barr
    -1.65
     strongh
    -1.63
    =-=-
    -1.61
    POSITIVE LOGITS
    Dad
    1.93
     toddler
    1.91
    Todd
    1.83
    Reader
    1.81
     floppy
    1.71
     diaper
    1.66
     intruder
    1.61
     dehyd
    1.60
    handler
    1.56
     Reggie
    1.56
    Activations Density 0.077%

    No Known Activations