© 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. 10-ATT-KK
    11. 13285
    Prev
    Next
    INDEX
    Explanations

    instances of color descriptions and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.37
    2:0.03
    3:0.07
    4:0.03
    5:0.01
    6:0.08
    7:0.10
    8:0.02
    9:0.02
    10:0.09
    11:0.05
    Negative Logits
    ォ
    -3.16
    Strong
    -2.99
    Drop
    -2.94
     trimmed
    -2.79
     Drop
    -2.76
     Bare
    -2.69
    aeus
    -2.55
    Weak
    -2.52
     tru
    -2.47
     Dub
    -2.46
    POSITIVE LOGITS
     Inter
    6.90
     inter
    6.71
    Inter
    6.49
    inter
    5.85
     INTER
    4.83
    INTER
    4.68
     interf
    4.45
     intra
    3.83
     interval
    3.46
     intervals
    3.24
    Activations Density 0.050%

    No Known Activations