© 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. 9-ATT-KK
    11. 354
    Prev
    Next
    INDEX
    Explanations

    political and legal references involving blame, accountability, and public statements

    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
    0:0.06
    1:0.02
    2:0.27
    3:0.16
    4:0.03
    5:0.05
    6:0.03
    7:0.06
    8:0.04
    9:0.04
    10:0.16
    11:0.03
    Negative Logits
     adversity
    -2.40
     situations
    -2.35
     situation
    -2.29
     kindness
    -2.26
     manners
    -2.26
     Volunte
    -2.21
     2100
    -2.18
     Younger
    -2.16
     friendships
    -2.13
     toughness
    -2.11
    POSITIVE LOGITS
     debunked
    2.68
     authenticated
    2.47
    uthor
    2.46
     dubbed
    2.43
     furiously
    2.40
     vehemently
    2.38
     billed
    2.32
    successfully
    2.29
     discredited
    2.29
    ���
    2.27
    Activations Density 0.075%

    No Known Activations