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. 8514
    Prev
    Next
    INDEX
    Explanations

    legal terms and judgments related to criminal activities

    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
    0:0.02
    1:0.06
    2:0.05
    3:0.04
    4:0.02
    5:0.06
    6:0.04
    7:0.06
    8:0.09
    9:0.34
    10:0.06
    11:0.10
    Negative Logits
    izons
    -1.67
    Vs
    -1.52
    angular
    -1.46
    hash
    -1.45
    DragonMagazine
    -1.40
     evolves
    -1.39
    PsyNetMessage
    -1.37
     unfolds
    -1.36
    groups
    -1.36
     onwards
    -1.34
    POSITIVE LOGITS
     wounding
    1.84
     manslaughter
    1.78
     Cruel
    1.62
     improper
    1.60
     treason
    1.59
     crimes
    1.58
     unlawful
    1.56
     violation
    1.53
     wrongdoing
    1.52
     tresp
    1.50
    Activations Density 0.030%

    No Known Activations