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

    Neuronpedia

    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. 5-ATT-KK
    11. 3068
    Prev
    Next
    INDEX
    Explanations

    terms related to the classification and containment procedures of SCP (Secure, Contain, Protect) objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.07
    3:0.15
    4:0.05
    5:0.04
    6:0.03
    7:0.18
    8:0.04
    9:0.07
    10:0.18
    11:0.09
    Negative Logits
     reckon
    -1.45
     woes
    -1.43
    �
    -1.43
    cil
    -1.42
     pas
    -1.31
     lamented
    -1.29
     trou
    -1.26
    YP
    -1.25
     sus
    -1.25
    Tab
    -1.24
    POSITIVE LOGITS
     Procedures
    1.56
     Rept
    1.50
     Canaver
    1.44
     Reincarn
    1.39
     Freeze
    1.38
     Cind
    1.37
     Clockwork
    1.36
     precaution
    1.31
    odge
    1.30
    pecially
    1.29
    Activations Density 0.001%

    No Known Activations