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. 9-ATT-KK
    6. 18646
    Prev
    Next
    INDEX
    Explanations

    legal terms related to theft and sentencing

    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
    2:0.45
    3:0.09
    4:0.03
    5:0.10
    6:0.03
    7:0.05
    8:0.05
    9:0.02
    10:0.03
    11:0.01
    Negative Logits
     nutrit
    -2.69
    metry
    -2.68
    ilater
    -2.68
     Uni
    -2.54
     pollen
    -2.46
    nas
    -2.38
    ◼
    -2.37
     UNESCO
    -2.35
     Asus
    -2.33
    ebus
    -2.30
    POSITIVE LOGITS
     sentencing
    6.80
     jail
    6.36
     convict
    6.26
    Prosecut
    6.13
     convicted
    5.95
    Prosecutors
    5.93
     criminal
    5.91
     prosecuting
    5.89
     prison
    5.86
     sentenced
    5.82
    Activations Density 2.336%

    No Known Activations