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. 3-ATT-KK
    6. 8430
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with event data, specifically dates and figures

    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
    0:0.19
    1:0.03
    2:0.08
    3:0.08
    4:0.14
    5:0.04
    6:0.06
    7:0.07
    8:0.05
    9:0.06
    10:0.11
    11:0.03
    Negative Logits
     equivalent
    -1.09
     Gy
    -1.07
    omorphic
    -1.06
     glide
    -1.03
    eworld
    -1.01
     flick
    -0.99
     fond
    -0.98
     marvel
    -0.96
     CrossRef
    -0.96
    opter
    -0.95
    POSITIVE LOGITS
    swers
    1.39
    iatus
    1.30
    acter
    1.19
     *)
    1.19
    ause
    1.17
    *)
    1.15
     Journals
    1.13
    aternity
    1.13
    reply
    1.12
    catentry
    1.12
    Activations Density 0.013%

    No Known Activations