© 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. 4864
    Prev
    Next
    INDEX
    Explanations

    classifications of living organisms along with nutritional information

    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
    0:0.35
    1:0.02
    2:0.09
    3:0.09
    4:0.05
    5:0.03
    6:0.03
    7:0.02
    8:0.06
    9:0.07
    10:0.06
    11:0.07
    Negative Logits
    asel
    -2.09
    kef
    -2.01
    idon
    -1.86
    conservancy
    -1.83
    kell
    -1.77
    ayne
    -1.74
    ahn
    -1.73
    infeld
    -1.67
    xus
    -1.66
     shif
    -1.65
    POSITIVE LOGITS
    iameter
    2.25
    %:
    2.23
     Avg
    2.02
     Sources
    1.92
     Locations
    1.89
     Features
    1.88
    :#
    1.84
     Potential
    1.80
    :"
    1.80
    ipment
    1.79
    Activations Density 0.102%

    No Known Activations