© 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. 43803
    Prev
    Next
    INDEX
    Explanations

    references to sports player positions and 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
    0:0.31
    1:0.02
    2:0.11
    3:0.04
    4:0.03
    5:0.04
    6:0.07
    7:0.02
    8:0.05
    9:0.07
    10:0.14
    11:0.04
    Negative Logits
    imar
    -1.97
    otrop
    -1.81
    anqu
    -1.76
    unction
    -1.74
    vernment
    -1.73
     SHALL
    -1.70
    estic
    -1.66
    omnia
    -1.65
    untary
    -1.64
    glomer
    -1.63
    POSITIVE LOGITS
    ENE
    1.94
    fx
    1.85
    .:
    1.72
    ��
    1.65
    :
    1.63
    Editor
    1.60
    ________________________________________________________________
    1.59
    /
    1.58
    Lastly
    1.58
     Notes
    1.58
    Activations Density 0.002%

    No Known Activations