© 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 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. 43515
    Prev
    Next
    INDEX
    Explanations

    phrases that express concern or refer to risks and uncertainties

    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
    2:0.07
    3:0.06
    4:0.33
    5:0.03
    6:0.03
    7:0.17
    8:0.03
    9:0.04
    10:0.07
    11:0.09
    Negative Logits
     innocence
    -1.64
    iphany
    -1.59
     disconnected
    -1.47
    eness
    -1.45
     metaphor
    -1.42
     feeling
    -1.40
     silence
    -1.40
     witness
    -1.40
     bitterness
    -1.38
    represented
    -1.38
    POSITIVE LOGITS
    lees
    1.68
    ossal
    1.58
    airs
    1.45
     Hels
    1.42
    ":{"
    1.41
     Locations
    1.40
     Garg
    1.39
    ��
    1.38
     Siem
    1.36
    jas
    1.36
    Activations Density 0.001%

    No Known Activations