© 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. 43433
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities and their associated attributes or actions

    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
    0:0.02
    1:0.01
    2:0.05
    3:0.07
    4:0.24
    5:0.02
    6:0.05
    7:0.33
    8:0.03
    9:0.02
    10:0.05
    11:0.06
    Negative Logits
    lance
    -1.45
    quartered
    -1.37
    wark
    -1.36
    olk
    -1.30
    gered
    -1.27
    rouse
    -1.25
    860
    -1.21
     YORK
    -1.19
    eln
    -1.19
    usk
    -1.17
    POSITIVE LOGITS
     names
    1.87
     positives
    1.85
     prominently
    1.75
     redacted
    1.68
     boxes
    1.62
     markers
    1.61
     lists
    1.59
     items
    1.58
     similarities
    1.54
     negatives
    1.51
    Activations Density 0.007%

    No Known Activations