© 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. 13658
    Prev
    Next
    INDEX
    Explanations

    statements related to health and recovery

    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
    1:0.02
    2:0.06
    3:0.03
    4:0.06
    5:0.04
    6:0.26
    7:0.03
    8:0.08
    9:0.24
    10:0.01
    11:0.04
    Negative Logits
     Tile
    -4.08
     Lei
    -4.02
     Gilmore
    -3.99
     Foley
    -3.91
    Lewis
    -3.91
     Rousse
    -3.75
    uner
    -3.59
     Doyle
    -3.47
     Lewis
    -3.44
     Hait
    -3.36
    POSITIVE LOGITS
    Av
    9.41
     Av
    9.41
     av
    9.08
     AV
    7.36
    AV
    7.00
     avocado
    6.73
    av
    6.21
     AZ
    4.84
     Avatar
    4.68
     Lav
    4.66
    Activations Density 0.010%

    No Known Activations