© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 9553
    Prev
    Next
    INDEX
    Explanations

    instances of governance, oversight, and environmental concerns

    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
    0:0.01
    1:0.01
    2:0.09
    3:0.08
    4:0.46
    5:0.02
    6:0.06
    7:0.08
    8:0.03
    9:0.02
    10:0.04
    11:0.04
    Negative Logits
     Unsure
    -1.74
     overcame
    -1.42
    ioned
    -1.40
     Registry
    -1.33
    umbn
    -1.32
     hadn
    -1.32
     Volunte
    -1.32
     interacted
    -1.31
     Played
    -1.29
     wasn
    -1.28
    POSITIVE LOGITS
    NetMessage
    1.50
     havoc
    1.43
     passage
    1.40
     Kinnikuman
    1.38
     horizont
    1.36
     overload
    1.34
     columns
    1.34
     indiscrim
    1.29
     contradictory
    1.27
     '.
    1.26
    Activations Density 0.319%

    No Known Activations