Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27502
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and gender roles

    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
    0:0.11
    1:0.09
    2:0.05
    3:0.08
    4:0.04
    5:0.09
    6:0.05
    7:0.02
    8:0.08
    9:0.14
    10:0.07
    11:0.11
    Negative Logits
    remlin
    -1.62
    imaru
    -1.60
    76561
    -1.57
    aughed
    -1.56
    ajor
    -1.55
    claimed
    -1.54
    edIn
    -1.53
    ento
    -1.52
    answered
    -1.51
    ailable
    -1.51
    POSITIVE LOGITS
     segregated
    1.48
     mascul
    1.46
     multicultural
    1.42
     Enlightenment
    1.27
     Esk
    1.26
     Cycling
    1.24
     Muslim
    1.22
     Emmanuel
    1.22
     mobilize
    1.22
     diversity
    1.21
    Activations Density 0.044%

    No Known Activations