© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 6084
    Prev
    Next
    INDEX
    Explanations

    elements associated with personal data and records

    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
    0:0.08
    1:0.05
    2:0.05
    3:0.02
    4:0.10
    5:0.27
    6:0.05
    7:0.07
    8:0.05
    9:0.03
    10:0.13
    11:0.05
    Negative Logits
    ahime
    -2.20
    uably
    -1.81
    ageddon
    -1.76
     Franch
    -1.73
     rallying
    -1.73
    rosso
    -1.68
    姫
    -1.67
     Canaver
    -1.63
     overshadowed
    -1.63
     Incarn
    -1.61
    POSITIVE LOGITS
     receipt
    2.40
     confidential
    2.16
     invoice
    2.06
     Pastebin
    2.04
     encrypted
    2.04
     password
    2.03
     redacted
    2.03
    itored
    2.02
     packet
    1.97
     mail
    1.96
    Activations Density 0.609%

    No Known Activations