© 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. 4924
    Prev
    Next
    INDEX
    Explanations

    mentions of drugs and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.01
    2:0.11
    3:0.11
    4:0.23
    5:0.04
    6:0.05
    7:0.10
    8:0.04
    9:0.04
    10:0.10
    11:0.10
    Negative Logits
    ynes
    -1.82
    roman
    -1.68
    thouse
    -1.65
    into
    -1.54
    eni
    -1.54
    PsyNetMessage
    -1.43
    vez
    -1.41
    jah
    -1.41
     Zamb
    -1.41
    undle
    -1.39
    POSITIVE LOGITS
     purposes
    1.80
     alterations
    1.71
     removal
    1.69
     hardness
    1.64
     tampering
    1.64
     significance
    1.62
     damage
    1.57
     effects
    1.56
     modifications
    1.52
     compatibility
    1.51
    Activations Density 0.002%

    No Known Activations