© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 43796
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating location or position

    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
    0:0.12
    1:0.05
    2:0.11
    3:0.06
    4:0.05
    5:0.08
    6:0.04
    7:0.07
    8:0.12
    9:0.07
    10:0.06
    11:0.12
    Negative Logits
     subscript
    -2.32
    standard
    -1.85
    fter
    -1.81
    attribute
    -1.78
    ivalent
    -1.76
    illance
    -1.71
    ティ
    -1.70
    enser
    -1.67
    イ
    -1.66
    displayText
    -1.65
    POSITIVE LOGITS
     Pil
    1.93
     Roh
    1.85
     Sonny
    1.85
     Glen
    1.82
     Vale
    1.79
     Bye
    1.76
     Manor
    1.75
     Ashe
    1.74
     Lyon
    1.72
     PJ
    1.71
    Activations Density 0.000%

    No Known Activations