© 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. 43191
    Prev
    Next
    INDEX
    Explanations

    references to goals and directions, particularly in the context of progress or movement toward specific objectives

    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
    1:0.01
    2:0.05
    3:0.07
    4:0.16
    5:0.03
    6:0.07
    7:0.32
    8:0.04
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
     bothers
    -1.52
     Koreans
    -1.45
     surname
    -1.39
     variables
    -1.35
     surn
    -1.33
     acron
    -1.30
    sites
    -1.29
     names
    -1.28
     Ezek
    -1.25
    }{
    -1.24
    POSITIVE LOGITS
    irtual
    1.87
     cures
    1.59
    antage
    1.58
     perfection
    1.57
     completion
    1.56
     vision
    1.56
     curing
    1.56
    irection
    1.55
     fruition
    1.52
     harmony
    1.51
    Activations Density 0.001%

    No Known Activations