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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 62
    Prev
    Next
    INDEX
    Explanations

    situations involving imprisonment or confinement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.01
    2:0.13
    3:0.38
    4:0.02
    5:0.08
    6:0.01
    7:0.04
    8:0.04
    9:0.01
    10:0.12
    11:0.01
    Negative Logits
     commenters
    -2.70
     contributions
    -2.45
     Flavoring
    -2.37
     Highlights
    -2.36
     readers
    -2.35
     listeners
    -2.34
     quotes
    -2.28
     users
    -2.28
     announcements
    -2.27
     signatures
    -2.27
    POSITIVE LOGITS
     detention
    3.87
     prison
    3.73
     confinement
    3.60
     Detention
    3.55
     prisons
    3.49
     jail
    3.48
    prison
    3.40
     jails
    3.29
     limbo
    3.23
     shack
    3.23
    Activations Density 0.456%

    No Known Activations