© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 1768
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to social responsibility and critiques of political actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.03
    3:0.14
    4:0.02
    5:0.04
    6:0.01
    7:0.04
    8:0.02
    9:0.01
    10:0.57
    11:0.02
    Negative Logits
     dedicate
    -2.28
     sufficiently
    -1.91
     contiguous
    -1.91
    Detailed
    -1.85
    neys
    -1.73
    ça
    -1.73
    ":"/
    -1.72
     "$:/
    -1.69
     immediately
    -1.67
     ahead
    -1.66
    POSITIVE LOGITS
     disadvantage
    2.92
     detriment
    2.67
     dismay
    2.57
     liking
    2.40
     amaz
    2.33
     disadvantages
    2.26
    limits
    2.25
     wondered
    2.20
     scorn
    2.19
     satisfaction
    2.18
    Activations Density 0.287%

    No Known Activations