© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 29981
    Prev
    Next
    INDEX
    Explanations

    specific locations or places mentioned in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.02
    3:0.03
    4:0.03
    5:0.46
    6:0.02
    7:0.01
    8:0.04
    9:0.10
    10:0.12
    11:0.05
    Negative Logits
    bear
    -1.73
    okia
    -1.71
    irit
    -1.68
    VIDIA
    -1.66
    abi
    -1.63
    bug
    -1.62
    xit
    -1.61
    strous
    -1.61
    ipl
    -1.60
     Trib
    -1.58
    POSITIVE LOGITS
     confines
    1.86
     clipboard
    1.75
    wide
    1.75
     borders
    1.72
     streets
    1.67
     doors
    1.65
     bathroom
    1.64
     hallway
    1.62
     locker
    1.62
     unfocusedRange
    1.58
    Activations Density 1.069%

    No Known Activations