© 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. 18977
    Prev
    Next
    INDEX
    Explanations

    topics related to news articles, particularly those concerning education and religion

    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
    2:0.04
    3:0.11
    4:0.07
    5:0.13
    6:0.03
    7:0.05
    8:0.06
    9:0.03
    10:0.06
    11:0.31
    Negative Logits
     [&
    -3.53
    >.
    -3.21
     «
    -3.07
     Profile
    -3.06
    ]).
    -3.00
    Newsletter
    -2.68
    >,
    -2.67
     Quote
    -2.64
    »
    -2.56
    ].
    -2.56
    POSITIVE LOGITS
    /
    3.16
    )/
    2.81
     /
    2.71
    /"
    2.70
     scam
    2.67
     rapist
    2.58
    /)
    2.53
     dad
    2.38
     daddy
    2.35
    /,
    2.35
    Activations Density 0.002%

    No Known Activations