© 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. 2-ATT-KK
    11. 22043
    Prev
    Next
    INDEX
    Explanations

    critical discussions around ethics and morality, particularly in the context of societal issues and government actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.03
    2:0.13
    3:0.07
    4:0.06
    5:0.20
    6:0.07
    7:0.03
    8:0.07
    9:0.10
    10:0.08
    11:0.03
    Negative Logits
    orsi
    -1.01
    ussions
    -1.00
    ificate
    -0.98
    alde
    -0.98
    incerity
    -0.96
    ustration
    -0.90
    ussion
    -0.89
     Timbers
    -0.88
    yip
    -0.86
     Downing
    -0.85
    POSITIVE LOGITS
    )</
    0.97
    ュ
    0.97
    pmwiki
    0.94
    !).
    0.91
    ).[
    0.90
    cffffcc
    0.88
    stellar
    0.86
    ニ
    0.86
    】
    0.85
    sonian
    0.84
    Activations Density 0.139%

    No Known Activations