© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43208
    Prev
    Next
    INDEX
    Explanations

    language related to charitable donations and fundraising efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.01
    2:0.09
    3:0.06
    4:0.11
    5:0.04
    6:0.03
    7:0.08
    8:0.04
    9:0.06
    10:0.32
    11:0.10
    Negative Logits
     tenure
    -1.73
     careers
    -1.50
     portfolios
    -1.48
     personality
    -1.43
     outper
    -1.43
     archetype
    -1.42
     ré
    -1.42
     portfolio
    -1.41
     career
    -1.40
     stereotype
    -1.36
    POSITIVE LOGITS
     Donation
    1.97
     rall
    1.96
    transfer
    1.69
     Proceed
    1.68
     transl
    1.62
    �
    1.61
    ilation
    1.60
    Transfer
    1.58
    ocument
    1.57
    athering
    1.52
    Activations Density 0.005%

    No Known Activations