© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 40343
    Prev
    Next
    INDEX
    Explanations

    references to criminals and various marginalized groups in the context of safety and community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.12
    3:0.13
    4:0.31
    5:0.02
    6:0.03
    7:0.10
    8:0.02
    9:0.05
    10:0.06
    11:0.07
    Negative Logits
    ��
    -1.97
    cknow
    -1.76
    ��
    -1.69
     calibrated
    -1.62
    SourceFile
    -1.58
    aito
    -1.47
    inventoryQuantity
    -1.47
     mirrored
    -1.46
    Haunted
    -1.46
    ested
    -1.45
    POSITIVE LOGITS
     purposes
    2.02
     newcomers
    1.82
     youngsters
    1.67
     families
    1.65
     crews
    1.62
     budding
    1.62
     flyers
    1.57
    ankind
    1.56
     generations
    1.56
     travellers
    1.52
    Activations Density 0.178%

    No Known Activations