© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 2872
    Prev
    Next
    INDEX
    Explanations

    terms related to health and safety violations

    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
    1:0.06
    2:0.12
    3:0.11
    4:0.08
    5:0.10
    6:0.05
    7:0.09
    8:0.07
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
     Frankenstein
    -2.60
    enegger
    -2.51
     creators
    -2.43
    eva
    -2.41
    ombies
    -2.40
     indo
    -2.40
    encers
    -2.38
    ppa
    -2.33
     actresses
    -2.32
     assassins
    -2.31
    POSITIVE LOGITS
     Parking
    2.77
    Minor
    2.69
     Penalty
    2.58
    Yellow
    2.56
     unfocusedRange
    2.48
     Significant
    2.45
    Number
    2.43
    Park
    2.39
    Past
    2.38
     Inspection
    2.38
    Activations Density 0.000%

    No Known Activations