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. 18728
    Prev
    Next
    INDEX
    Explanations

    phrases related to sentencing and prison terms

    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
    0:0.06
    1:0.01
    2:0.14
    3:0.22
    4:0.02
    5:0.11
    6:0.02
    7:0.12
    8:0.05
    9:0.02
    10:0.15
    11:0.01
    Negative Logits
     chatter
    -2.32
     speakers
    -2.25
    Reply
    -2.21
     announcements
    -2.00
    groups
    -1.97
     bandwagon
    -1.97
     Groups
    -1.93
     speaker
    -1.92
     singers
    -1.90
     actors
    -1.90
    POSITIVE LOGITS
     jail
    3.08
     prison
    3.02
     sentencing
    2.99
     imprisonment
    2.96
     punishment
    2.85
     punishments
    2.67
     sentenced
    2.65
     restitution
    2.60
     manslaughter
    2.59
    uries
    2.55
    Activations Density 0.017%

    No Known Activations