© 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. 5-ATT-KK
    11. 27764
    Prev
    Next
    INDEX
    Explanations

    expressions of solidarity and support for various groups and causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.06
    3:0.06
    4:0.10
    5:0.03
    6:0.02
    7:0.38
    8:0.02
    9:0.03
    10:0.12
    11:0.10
    Negative Logits
     puberty
    -1.64
     Xan
    -1.62
    doctor
    -1.45
    imester
    -1.43
    mental
    -1.39
     pills
    -1.39
     Reincarn
    -1.34
    metadata
    -1.30
    rollment
    -1.29
     kale
    -1.29
    POSITIVE LOGITS
     plight
    1.66
    MpServer
    1.62
     solidarity
    1.59
    against
    1.53
     brothers
    1.40
     uncond
    1.40
     downt
    1.39
     persecuted
    1.38
     kindred
    1.36
     agg
    1.35
    Activations Density 0.002%

    No Known Activations