© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14250
    Prev
    Next
    INDEX
    Explanations

    phrases related to psychiatric treatment and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.05
    2:0.06
    3:0.05
    4:0.07
    5:0.03
    6:0.08
    7:0.20
    8:0.03
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
     Wiggins
    -2.65
     Sprint
    -2.59
     Tourism
    -2.58
     Kuwait
    -2.52
     Mau
    -2.51
     aer
    -2.49
     Cer
    -2.48
     rider
    -2.47
     Thib
    -2.44
     Passenger
    -2.43
    POSITIVE LOGITS
    sych
    2.98
     Arkham
    2.52
     psychiatrists
    2.51
     goblin
    2.47
     Psychiatry
    2.45
     goblins
    2.43
    idth
    2.43
    mouse
    2.40
    gob
    2.40
     Gors
    2.40
    Activations Density 0.001%

    No Known Activations