© 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. 9-ATT-KK
    11. 13470
    Prev
    Next
    INDEX
    Explanations

    phrases related to the relationship between street drug use and schizophrenia development

    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
    0:0.11
    1:0.03
    2:0.18
    3:0.06
    4:0.03
    5:0.07
    6:0.11
    7:0.05
    8:0.09
    9:0.13
    10:0.04
    11:0.04
    Negative Logits
     lubric
    -3.62
    Oil
    -3.37
     Aqua
    -3.34
    Water
    -3.25
    ubric
    -3.24
     Aero
    -3.23
    airo
    -3.20
     Xie
    -3.16
    waters
    -3.15
     waterproof
    -3.13
    POSITIVE LOGITS
     schizophrenia
    8.31
     schizophren
    7.92
     psychosis
    7.44
     psychotic
    6.45
    izophren
    6.10
     hallucinations
    5.45
     delusions
    5.25
     psychiatric
    5.17
     psychiatrists
    5.04
     psychiatry
    5.04
    Activations Density 0.006%

    No Known Activations