© 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. 45086
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of moving forward or making progress in life

    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
    1:0.02
    2:0.07
    3:0.06
    4:0.22
    5:0.02
    6:0.10
    7:0.30
    8:0.02
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
    ovan
    -1.45
     resided
    -1.43
    locks
    -1.39
     retri
    -1.39
    onite
    -1.37
     netted
    -1.36
     enters
    -1.34
    assium
    -1.33
     landfill
    -1.31
     translates
    -1.31
    POSITIVE LOGITS
    CLASSIFIED
    1.78
    Reviewer
    1.64
    Fight
    1.63
    Race
    1.51
    �
    1.47
    Compl
    1.47
    Story
    1.45
    Manufact
    1.44
    DonaldTrump
    1.44
    vironment
    1.42
    Activations Density 0.001%

    No Known Activations