© 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. 41523
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns indicating people involved in 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
    0:0.05
    1:0.03
    2:0.06
    3:0.05
    4:0.17
    5:0.10
    6:0.03
    7:0.16
    8:0.04
    9:0.06
    10:0.07
    11:0.12
    Negative Logits
     Carrier
    -1.55
     Patent
    -1.29
    uble
    -1.26
    onomic
    -1.22
    cus
    -1.22
    inement
    -1.20
     Sale
    -1.20
    drawn
    -1.20
    PU
    -1.18
    loading
    -1.17
    POSITIVE LOGITS
    DERR
    1.39
     STORY
    1.35
     Dawn
    1.27
    psc
    1.27
     verbally
    1.26
    ITNESS
    1.25
     newsp
    1.24
     unaff
    1.21
     Duff
    1.19
     psychiatrists
    1.19
    Activations Density 0.021%

    No Known Activations