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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 8785
    Prev
    Next
    INDEX
    Explanations

    instances of various social issues and their impact on communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.34
    1:0.03
    2:0.02
    3:0.05
    4:0.04
    5:0.07
    6:0.07
    7:0.18
    8:0.03
    9:0.06
    10:0.01
    11:0.06
    Negative Logits
    ACTED
    -2.08
     Located
    -2.00
    agree
    -2.00
    Normally
    -1.98
     ordinarily
    -1.97
     Normally
    -1.92
     Originally
    -1.89
     liked
    -1.88
    stood
    -1.86
     theirs
    -1.85
    POSITIVE LOGITS
    ullah
    1.99
     tuberculosis
    1.96
     migration
    1.94
     therapies
    1.92
     cures
    1.90
     interventions
    1.89
     parenting
    1.88
     restoration
    1.85
     strategies
    1.82
     wisdom
    1.80
    Activations Density 0.184%

    No Known Activations