© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 11782
    Prev
    Next
    INDEX
    Explanations

    informative content such as news articles and newsletter subscription details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to subscription and sign-up offers for newsletters or clubs

    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
    0:0.02
    1:0.08
    2:0.10
    3:0.06
    4:0.02
    5:0.11
    6:0.07
    7:0.09
    8:0.10
    9:0.14
    10:0.07
    11:0.10
    Negative Logits
    etheless
    -2.03
    chwitz
    -1.66
    livious
    -1.61
    wcs
    -1.61
     transpired
    -1.60
    uably
    -1.56
    nces
    -1.55
    sov
    -1.54
    bably
    -1.53
     cannibal
    -1.52
    POSITIVE LOGITS
     subscription
    1.69
     Subscribe
    1.58
     Scrib
    1.57
     bookmark
    1.54
     Membership
    1.52
    Pinterest
    1.51
     Notification
    1.50
     newsletter
    1.49
     Editorial
    1.49
     Newsletter
    1.47
    Activations Density 0.019%

    No Known Activations