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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20661
    Prev
    Next
    INDEX
    Explanations

    instances of words related to criminal law and justice

    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
    0:0.04
    1:0.04
    2:0.07
    3:0.11
    4:0.09
    5:0.09
    6:0.03
    7:0.35
    8:0.02
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
    roud
    -2.42
    ernels
    -2.39
    WD
    -2.30
    senal
    -2.25
    umbers
    -2.25
    wx
    -2.24
    redients
    -2.10
     Tud
    -2.05
    idents
    -2.05
    mega
    -2.04
    POSITIVE LOGITS
     his
    4.30
    his
    4.01
     himself
    3.97
     he
    3.80
     him
    3.63
    His
    3.50
    He
    3.29
    him
    3.21
     His
    3.09
     He
    2.96
    Activations Density 0.667%

    No Known Activations