© 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. 10087
    Prev
    Next
    INDEX
    Explanations

    phrases related to community events and LGBTQ+ support

    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
    0:0.09
    1:0.03
    2:0.18
    3:0.05
    4:0.04
    5:0.06
    6:0.16
    7:0.06
    8:0.10
    9:0.10
    10:0.03
    11:0.04
    Negative Logits
    ochem
    -3.92
    ochemical
    -3.84
    worm
    -3.58
     therm
    -3.57
    conom
    -3.52
     cellar
    -3.49
     retri
    -3.25
    atom
    -3.25
     deposit
    -3.23
    _.
    -3.19
    POSITIVE LOGITS
     Pride
    9.73
     pride
    5.94
     LGBTQ
    5.38
     parade
    5.30
     homophobia
    5.14
     rainbow
    4.90
     queer
    4.78
     Parade
    4.78
    LGBT
    4.78
     Gay
    4.76
    Activations Density 0.002%

    No Known Activations