© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43247
    Prev
    Next
    INDEX
    Explanations

    geographical regions or directional terms

    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
    0:0.27
    1:0.03
    2:0.08
    3:0.04
    4:0.05
    5:0.04
    6:0.06
    7:0.02
    8:0.17
    9:0.04
    10:0.06
    11:0.08
    Negative Logits
     spar
    -1.92
    offer
    -1.78
     inspecting
    -1.70
     spraying
    -1.67
     swapping
    -1.65
     linkage
    -1.64
     suggesting
    -1.61
     filler
    -1.60
     teasing
    -1.60
     sizing
    -1.59
    POSITIVE LOGITS
    amia
    2.05
    sburgh
    1.80
    TED
    1.80
    elaide
    1.80
    conom
    1.79
    iety
    1.76
    outheastern
    1.66
    Republic
    1.65
    imensional
    1.65
    Commerce
    1.62
    Activations Density 0.003%

    No Known Activations