© 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. 9-ATT-KK
    11. 20377
    Prev
    Next
    INDEX
    Explanations

    concepts related to consciousness and perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.04
    2:0.20
    3:0.07
    4:0.04
    5:0.08
    6:0.11
    7:0.05
    8:0.08
    9:0.12
    10:0.04
    11:0.02
    Negative Logits
    Upgrade
    -3.38
     spoil
    -2.98
    姫
    -2.97
    inelli
    -2.94
    Spain
    -2.79
     Blazers
    -2.77
    replace
    -2.71
     refurb
    -2.69
     Wyatt
    -2.66
    thora
    -2.64
    POSITIVE LOGITS
     Conscious
    6.62
     consciousness
    6.44
     conscious
    5.87
    conscious
    5.44
     unconscious
    4.94
     subconscious
    4.80
     consciously
    4.73
     trance
    4.72
     awareness
    4.37
     EEG
    4.33
    Activations Density 0.006%

    No Known Activations