© 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. 9-ATT-KK
    11. 2788
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their actions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.07
    3:0.24
    4:0.02
    5:0.08
    6:0.02
    7:0.07
    8:0.03
    9:0.02
    10:0.29
    11:0.03
    Negative Logits
    olesc
    -2.32
    ovember
    -2.16
    update
    -2.15
     volley
    -2.04
     tomorrow
    -2.03
     rebirth
    -1.98
     unveiling
    -1.97
     continuum
    -1.96
    EStreamFrame
    -1.95
    ihilation
    -1.95
    POSITIVE LOGITS
     lacked
    3.49
     lacks
    3.04
     disliked
    2.75
     smelled
    2.60
     disple
    2.55
    didn
    2.51
     bothered
    2.49
     dislike
    2.49
     didn
    2.47
     wanted
    2.41
    Activations Density 0.194%

    No Known Activations