© 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. 44754
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate capability or potential, specifically focusing on the word "ability" followed by an action or goal

    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
    2:0.12
    3:0.08
    4:0.07
    5:0.02
    6:0.04
    7:0.35
    8:0.03
    9:0.03
    10:0.08
    11:0.08
    Negative Logits
    bris
    -1.48
    cock
    -1.45
     aback
    -1.42
    anmar
    -1.38
     hotly
    -1.36
    ussions
    -1.35
    worn
    -1.34
     ensued
    -1.32
    akov
    -1.32
    abeth
    -1.29
    POSITIVE LOGITS
     access
    1.55
     limitless
    1.53
    mable
    1.52
     unlimited
    1.51
     automatic
    1.50
     flexibility
    1.49
     ability
    1.37
     leverage
    1.36
     levers
    1.35
     backdoor
    1.34
    Activations Density 0.014%

    No Known Activations