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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43231
    Prev
    Next
    INDEX
    Explanations

    references to collaborative community efforts or partnerships

    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
    0:0.01
    1:0.01
    2:0.09
    3:0.31
    4:0.09
    5:0.04
    6:0.02
    7:0.08
    8:0.04
    9:0.05
    10:0.11
    11:0.09
    Negative Logits
     msec
    -1.63
    ighed
    -1.48
    toggle
    -1.45
     Tests
    -1.34
    Enlarge
    -1.32
    taboola
    -1.31
    /(
    -1.31
    equ
    -1.30
     Britons
    -1.28
     factors
    -1.28
    POSITIVE LOGITS
     responsibly
    1.95
    dinand
    1.74
     pione
    1.65
     myself
    1.57
     ourselves
    1.54
     volunte
    1.53
    rolet
    1.53
    etsy
    1.51
     boldly
    1.50
     redes
    1.46
    Activations Density 0.230%

    No Known Activations