© 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. 10-ATT-KK
    11. 13860
    Prev
    Next
    INDEX
    Explanations

    names and references to individuals involved in specific incidents or allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.02
    2:0.03
    3:0.04
    4:0.11
    5:0.47
    6:0.02
    7:0.04
    8:0.02
    9:0.10
    10:0.02
    11:0.04
    Negative Logits
    Discussion
    -2.95
    assian
    -2.87
    =-=-=-=-=-=-=-=-
    -2.85
    Alternatively
    -2.76
    available
    -2.63
    )?
    -2.51
     Alternatively
    -2.44
    agi
    -2.43
    amiliar
    -2.42
    itters
    -2.39
    POSITIVE LOGITS
     blew
    3.53
     regrets
    3.50
     stole
    3.43
     owes
    3.38
     caused
    3.24
     violated
    3.22
     misled
    3.19
     deceived
    3.17
     woke
    3.09
     lied
    3.09
    Activations Density 0.368%

    No Known Activations