© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 23881
    Prev
    Next
    INDEX
    Explanations

    phrases indicating concern or caution regarding health or safety issues

    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
    0:0.21
    1:0.02
    2:0.17
    3:0.06
    4:0.03
    5:0.07
    6:0.13
    7:0.04
    8:0.07
    9:0.10
    10:0.03
    11:0.02
    Negative Logits
    ynchronous
    -3.18
    ARR
    -3.14
     GOODMAN
    -3.10
     adrenaline
    -2.90
     cru
    -2.78
     GPS
    -2.71
     Samar
    -2.68
    etooth
    -2.64
    Param
    -2.62
     Dawkins
    -2.61
    POSITIVE LOGITS
     mold
    8.40
     mould
    6.59
     Mold
    6.12
     molded
    5.48
     sculpt
    4.44
     spores
    4.30
    Maker
    3.89
    olds
    3.64
     Maker
    3.61
    ulpt
    3.60
    Activations Density 0.002%

    No Known Activations