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. 7501
    Prev
    Next
    INDEX
    Explanations

    references to socioeconomic status and the marginalized in society

    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
    0:0.22
    1:0.00
    2:0.13
    3:0.03
    4:0.08
    5:0.04
    6:0.06
    7:0.03
    8:0.16
    9:0.03
    10:0.08
    11:0.07
    Negative Logits
     groundwork
    -1.83
    ���
    -1.73
    ゴン
    -1.68
     memorandum
    -1.67
     memo
    -1.66
     outlining
    -1.65
     morp
    -1.64
     estimating
    -1.59
     checklist
    -1.57
     forwarding
    -1.57
    POSITIVE LOGITS
     alike
    2.62
    rier
    1.89
    rals
    1.79
    glers
    1.77
    iers
    1.76
    urers
    1.74
    esters
    1.72
    vertis
    1.70
    riger
    1.67
    rers
    1.65
    Activations Density 0.011%

    No Known Activations