© 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. 43860
    Prev
    Next
    INDEX
    Explanations

    phrases that lead into video content or call for continued engagement

    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
    2:0.06
    3:0.13
    4:0.09
    5:0.02
    6:0.21
    7:0.16
    8:0.05
    9:0.05
    10:0.09
    11:0.06
    Negative Logits
    restrial
    -1.50
     Directive
    -1.36
    76561
    -1.36
    ocally
    -1.34
     goodwill
    -1.26
     Lisp
    -1.25
     itself
    -1.25
     innate
    -1.24
     consensual
    -1.23
     embodied
    -1.22
    POSITIVE LOGITS
    croft
    1.99
     enlarge
    1.45
     circles
    1.42
    ]'
    1.40
     slideshow
    1.39
     clip
    1.38
     Featured
    1.38
     captcha
    1.35
     sidebar
    1.34
    >>
    1.33
    Activations Density 0.001%

    No Known Activations