© 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. 42049
    Prev
    Next
    INDEX
    Explanations

    references to geographical directions or divisions, particularly in sports contexts

    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
    1:0.03
    2:0.11
    3:0.05
    4:0.05
    5:0.07
    6:0.08
    7:0.06
    8:0.04
    9:0.06
    10:0.29
    11:0.08
    Negative Logits
     luggage
    -1.81
     torches
    -1.69
     pedals
    -1.69
    request
    -1.62
     accomp
    -1.59
     loudspe
    -1.57
     consultations
    -1.57
    respond
    -1.57
     Resp
    -1.57
    Materials
    -1.57
    POSITIVE LOGITS
     Division
    2.04
     edge
    1.99
     division
    1.98
    ldom
    1.92
    ancial
    1.91
     Playoff
    1.82
    nces
    1.81
     Championship
    1.79
     relegation
    1.78
     championships
    1.77
    Activations Density 0.003%

    No Known Activations