© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 8519
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hesitation or unwillingness to take action

    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
    0:0.02
    1:0.02
    2:0.08
    3:0.07
    4:0.08
    5:0.04
    6:0.05
    7:0.35
    8:0.02
    9:0.04
    10:0.07
    11:0.11
    Negative Logits
    ummies
    -1.43
    loo
    -1.39
    tainment
    -1.37
    abyte
    -1.36
    rification
    -1.32
    rings
    -1.32
     Rig
    -1.31
    lude
    -1.31
    itures
    -1.31
    Stars
    -1.31
    POSITIVE LOGITS
     permitting
    1.80
     dissenting
    1.55
     permit
    1.53
     pron
    1.39
    Reply
    1.37
     acknow
    1.35
     stringent
    1.34
     Flavoring
    1.34
     admitting
    1.33
     petition
    1.32
    Activations Density 0.010%

    No Known Activations