© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14895
    Prev
    Next
    INDEX
    Explanations

    content related to criminal accusations involving minors

    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
    1:0.02
    2:0.06
    3:0.06
    4:0.06
    5:0.03
    6:0.23
    7:0.06
    8:0.08
    9:0.23
    10:0.02
    11:0.03
    Negative Logits
     Haj
    -4.42
    ollah
    -4.00
     Zoro
    -3.71
     Ibn
    -3.69
    ゴン
    -3.65
    atomic
    -3.43
    AAF
    -3.39
     Alv
    -3.28
     liver
    -3.28
    AA
    -3.27
    POSITIVE LOGITS
     Peters
    11.41
     Petersen
    5.68
    Pet
    5.27
     PET
    5.14
     Pet
    4.94
    PET
    4.86
    pet
    4.74
     Peterson
    4.69
     Pets
    4.47
     Peck
    4.45
    Activations Density 0.001%

    No Known Activations