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. 8581
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocacy and support for various causes or groups

    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
    0:0.01
    1:0.04
    2:0.09
    3:0.18
    4:0.01
    5:0.02
    6:0.07
    7:0.10
    8:0.07
    9:0.19
    10:0.08
    11:0.07
    Negative Logits
    kes
    -1.19
     tallied
    -1.11
     Nielsen
    -1.05
    hook
    -1.04
    eye
    -1.04
     Seymour
    -1.03
    ftime
    -1.01
    iak
    -1.01
    akia
    -0.95
     digest
    -0.95
    POSITIVE LOGITS
     advoc
    1.13
    essim
    1.11
     Patients
    1.07
    Choice
    1.04
     Ending
    1.01
     advocating
    0.99
    FLAG
    0.98
     ideals
    0.97
     Limits
    0.97
     lowering
    0.97
    Activations Density 0.015%

    No Known Activations