© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 21518
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of giving a voice to marginalized communities

    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
    0:0.03
    1:0.03
    2:0.07
    3:0.07
    4:0.18
    5:0.04
    6:0.05
    7:0.27
    8:0.03
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
     Janeiro
    -1.60
     finishes
    -1.59
    ellery
    -1.50
     Rings
    -1.50
    agus
    -1.48
    upuncture
    -1.44
    finished
    -1.44
    pleted
    -1.44
     cabbage
    -1.42
    anium
    -1.42
    POSITIVE LOGITS
     society
    1.69
     norms
    1.65
     minorities
    1.63
     diversity
    1.60
    Reviewer
    1.60
    ��
    1.57
     Transgender
    1.55
     dissent
    1.53
     Indigenous
    1.52
     authority
    1.52
    Activations Density 0.000%

    No Known Activations