© 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. 22372
    Prev
    Next
    INDEX
    Explanations

    statements related to the impact and effectiveness of various systems or policies

    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
    0:0.04
    1:0.04
    2:0.10
    3:0.27
    4:0.11
    5:0.07
    6:0.04
    7:0.12
    8:0.06
    9:0.03
    10:0.06
    11:0.02
    Negative Logits
     fucking
    -2.70
     whilst
    -2.67
     offence
    -2.56
     assassinate
    -2.55
    stab
    -2.52
    ────
    -2.46
     Whilst
    -2.43
    Fuck
    -2.42
     humour
    -2.38
     ****
    -2.38
    POSITIVE LOGITS
     nonprofits
    3.13
     economists
    2.94
     critics
    2.94
    Enlarge
    2.88
     nonprofit
    2.88
     advocates
    2.87
     regulators
    2.86
     skeptics
    2.83
     analysts
    2.81
     pricey
    2.68
    Activations Density 1.138%

    No Known Activations