Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 7815
    Prev
    Next
    INDEX
    Explanations

    references to specific substances or medications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.06
    2:0.09
    3:0.18
    4:0.05
    5:0.04
    6:0.08
    7:0.14
    8:0.06
    9:0.08
    10:0.06
    11:0.08
    Negative Logits
    llor
    -1.31
    iets
    -1.13
    ruit
    -1.08
    ugi
    -1.07
    rider
    -1.06
    arios
    -1.05
     Objective
    -1.04
    lich
    -1.03
     crafts
    -1.03
    Keefe
    -1.03
    POSITIVE LOGITS
    */(
    1.49
    pload
    1.35
     Thumbnails
    1.33
     intangible
    1.28
     Cosponsors
    1.23
     slightest
    1.19
    ancial
    1.17
    endment
    1.11
    anship
    1.09
    perture
    1.09
    Activations Density 0.004%

    No Known Activations