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. 7177
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their roles or actions

    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
    0:0.04
    1:0.43
    2:0.03
    3:0.03
    4:0.03
    5:0.17
    6:0.04
    7:0.02
    8:0.04
    9:0.04
    10:0.06
    11:0.02
    Negative Logits
     STATS
    -2.36
     picnic
    -1.81
     moderates
    -1.80
     Tiny
    -1.73
     medi
    -1.72
     pint
    -1.71
     medic
    -1.71
     toilets
    -1.66
     sid
    -1.63
     NYT
    -1.61
    POSITIVE LOGITS
    au
    2.98
    ascript
    2.39
    aus
    2.36
    amac
    2.36
    aru
    2.16
    ape
    2.15
    aw
    2.14
    uve
    2.12
    ek
    2.12
    usk
    2.10
    Activations Density 0.003%

    No Known Activations