© 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. 5-ATT-KK
    11. 43634
    Prev
    Next
    INDEX
    Explanations

    phrases or constructs indicating quantities or measurements

    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
    0:0.03
    1:0.02
    2:0.07
    3:0.04
    4:0.06
    5:0.02
    6:0.23
    7:0.27
    8:0.04
    9:0.03
    10:0.10
    11:0.04
    Negative Logits
    soDeliveryDate
    -1.70
    enary
    -1.61
    �
    -1.60
     Bye
    -1.56
    study
    -1.54
    yssey
    -1.49
    RIPT
    -1.47
    rences
    -1.46
     Oral
    -1.46
    2019
    -1.42
    POSITIVE LOGITS
     weights
    1.98
     lbs
    1.89
    lbs
    1.86
     pounds
    1.86
    leeve
    1.76
     needles
    1.74
     unloaded
    1.73
     sacks
    1.72
     dough
    1.71
     guts
    1.66
    Activations Density 0.002%

    No Known Activations