© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 36167
    Prev
    Next
    INDEX
    Explanations

    words related to control and influence over actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.05
    3:0.05
    4:0.14
    5:0.02
    6:0.06
    7:0.39
    8:0.03
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
    ortium
    -2.21
    alach
    -1.92
    ilion
    -1.87
    ukemia
    -1.75
    icter
    -1.63
    abeth
    -1.60
    osponsors
    -1.58
    igham
    -1.57
    fal
    -1.54
    iversary
    -1.52
    POSITIVE LOGITS
     resh
    1.83
     dictated
    1.81
     directives
    1.75
     dictates
    1.68
     lapt
    1.65
     dictate
    1.63
     directions
    1.63
     ration
    1.62
     dict
    1.61
     quotas
    1.60
    Activations Density 0.005%

    No Known Activations