© 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. 3667
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and social issues affecting communities

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.09
    3:0.07
    4:0.40
    5:0.03
    6:0.03
    7:0.12
    8:0.03
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
     shalt
    -1.75
     reb
    -1.72
     disclaim
    -1.70
     faked
    -1.69
     guilt
    -1.68
     transpired
    -1.65
     existed
    -1.63
     cooperating
    -1.61
     reinvent
    -1.58
     blame
    -1.55
    POSITIVE LOGITS
     heights
    1.80
    reshold
    1.78
    gerald
    1.78
    BLIC
    1.73
    roads
    1.70
    ahn
    1.65
    ometown
    1.63
     LEVEL
    1.62
    ゼ
    1.61
    ワン
    1.60
    Activations Density 0.039%

    No Known Activations