© 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. 5-ATT-KK
    11. 42894
    Prev
    Next
    INDEX
    Explanations

    instances of possessive pronouns and references to projects or related actions

    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
    0:0.03
    1:0.02
    2:0.05
    3:0.07
    4:0.26
    5:0.03
    6:0.10
    7:0.18
    8:0.05
    9:0.04
    10:0.05
    11:0.07
    Negative Logits
    oco
    -1.33
    田
    -1.25
    anooga
    -1.22
    atures
    -1.19
     Sigma
    -1.18
    glers
    -1.18
    nces
    -1.17
    IFIED
    -1.17
    Reply
    -1.16
    ELY
    -1.16
    POSITIVE LOGITS
     scraps
    1.30
     recess
    1.30
     ceases
    1.29
     becomes
    1.26
     racks
    1.26
     leaves
    1.25
     finishes
    1.24
     occupies
    1.24
     bye
    1.24
    itiz
    1.23
    Activations Density 0.053%

    No Known Activations