© 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. 41925
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their relationships with various groups

    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
    0:0.02
    1:0.02
    2:0.11
    3:0.11
    4:0.35
    5:0.02
    6:0.04
    7:0.06
    8:0.03
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
    acca
    -1.80
    onement
    -1.58
     ______
    -1.50
     transitioned
    -1.50
     pir
    -1.49
    _(
    -1.48
     existed
    -1.47
    sac
    -1.46
    artifacts
    -1.45
    achev
    -1.42
    POSITIVE LOGITS
    ographers
    2.49
     analysts
    2.33
     reviewers
    2.29
     onlook
    2.29
    izens
    2.06
    ographer
    2.03
     interviewer
    2.00
     biologists
    1.97
     inspectors
    1.96
     pundits
    1.95
    Activations Density 0.166%

    No Known Activations