© 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. 5-ATT-KK
    11. 20851
    Prev
    Next
    INDEX
    Explanations

    emotional or safety-related themes in contexts involving relationships or personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.02
    2:0.10
    3:0.05
    4:0.11
    5:0.03
    6:0.44
    7:0.04
    8:0.04
    9:0.03
    10:0.05
    11:0.03
    Negative Logits
    ashtra
    -1.69
    orically
    -1.49
    yip
    -1.46
    racuse
    -1.35
    apsed
    -1.34
    adish
    -1.32
    esy
    -1.30
     unison
    -1.28
    qqa
    -1.27
    gow
    -1.27
    POSITIVE LOGITS
     selves
    1.37
     Territories
    1.29
    ISS
    1.18
    nesses
    1.17
     LLP
    1.13
     dealings
    1.10
    HCR
    1.09
     Painter
    1.07
    blood
    1.07
    iations
    1.07
    Activations Density 0.036%

    No Known Activations