© 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. 36896
    Prev
    Next
    INDEX
    Explanations

    conditional or contrasting phrases regarding outcomes and implications

    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
    2:0.11
    3:0.32
    4:0.15
    5:0.04
    6:0.04
    7:0.05
    8:0.05
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
    .''.
    -1.83
    )</
    -1.72
    FAQ
    -1.68
    )."
    -1.67
    .''
    -1.58
    cellaneous
    -1.57
    #$#$
    -1.55
    ancial
    -1.54
    optional
    -1.54
    lease
    -1.52
    POSITIVE LOGITS
     suddenly
    1.66
     overpower
    1.48
     strangers
    1.48
     juxtap
    1.44
     awful
    1.40
     oneself
    1.39
     bad
    1.39
     inherently
    1.38
     bullies
    1.37
     terrible
    1.36
    Activations Density 0.007%

    No Known Activations