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. 7238
    Prev
    Next
    INDEX
    Explanations

    mentions of events, especially regarding their status, attendance, and outcomes

    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
    1:0.01
    2:0.06
    3:0.06
    4:0.05
    5:0.04
    6:0.03
    7:0.04
    8:0.03
    9:0.07
    10:0.44
    11:0.10
    Negative Logits
     tails
    -1.69
     synt
    -1.64
     genes
    -1.64
    osate
    -1.60
     foreclosure
    -1.58
     Siberian
    -1.55
     transistor
    -1.49
     neurons
    -1.48
     generations
    -1.43
    ween
    -1.42
    POSITIVE LOGITS
     organisers
    2.31
     organizers
    2.08
     attendees
    1.98
     billed
    1.94
    iquette
    1.91
    iannopoulos
    1.82
     venue
    1.82
    goers
    1.77
     organizer
    1.70
     Particip
    1.67
    Activations Density 0.039%

    No Known Activations