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. 10378
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate substantial impacts, consequences, or transformations

    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
    1:0.05
    2:0.12
    3:0.03
    4:0.02
    5:0.05
    6:0.08
    7:0.04
    8:0.25
    9:0.14
    10:0.08
    11:0.07
    Negative Logits
    76561
    -1.21
    cffffcc
    -1.12
    Connector
    -1.09
    Holy
    -1.08
     Oops
    -0.99
    inus
    -0.98
    Was
    -0.97
     Didn
    -0.97
    quart
    -0.96
     wore
    -0.95
    POSITIVE LOGITS
     tomorrow
    1.51
     hereafter
    1.47
    morrow
    1.35
     someday
    1.30
    ezvous
    1.22
    continue
    1.18
     continue
    1.16
    vale
    1.16
    ugi
    1.15
    ample
    1.11
    Activations Density 0.407%

    No Known Activations