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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 8322
    Prev
    Next
    INDEX
    Explanations

    patterns of charitable actions or giving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.33
    1:0.04
    2:0.05
    3:0.05
    4:0.06
    5:0.08
    6:0.08
    7:0.05
    8:0.06
    9:0.03
    10:0.10
    11:0.02
    Negative Logits
    =#
    -1.45
     ¥
    -1.42
    ェ
    -1.39
     Pear
    -1.38
     Chap
    -1.37
     ����
    -1.35
     [+
    -1.35
    )|
    -1.35
     [&
    -1.35
     RAD
    -1.35
    POSITIVE LOGITS
    odied
    1.76
    atern
    1.72
    anos
    1.54
    aternal
    1.54
    shall
    1.48
    abolic
    1.46
    ration
    1.46
    answer
    1.45
    schild
    1.43
    according
    1.42
    Activations Density 0.116%

    No Known Activations