© 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. 5-ATT-KK
    11. 43558
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating personal relationships or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.07
    1:0.04
    2:0.10
    3:0.08
    4:0.07
    5:0.13
    6:0.04
    7:0.05
    8:0.20
    9:0.06
    10:0.05
    11:0.05
    Negative Logits
     ancest
    -1.75
    alach
    -1.75
     challeng
    -1.71
    pta
    -1.61
    atown
    -1.60
    aine
    -1.56
    hedon
    -1.53
    odan
    -1.52
    agine
    -1.51
    puter
    -1.51
    POSITIVE LOGITS
    invoke
    1.53
    ía
    1.50
    aeus
    1.47
    ERY
    1.45
     disconnected
    1.43
    ICES
    1.43
     CentOS
    1.42
    REC
    1.42
    toggle
    1.41
    VICE
    1.41
    Activations Density 0.000%

    No Known Activations