Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 9164
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.22
    1:0.01
    2:0.01
    3:0.05
    4:0.01
    5:0.31
    6:0.03
    7:0.01
    8:0.27
    9:0.02
    10:0.00
    11:0.00
    Negative Logits
     weights
    -2.09
    ylene
    -2.06
    epad
    -2.05
     ital
    -2.05
     parentheses
    -1.95
    olini
    -1.93
    ertodd
    -1.85
    isine
    -1.85
     designer
    -1.84
     appropri
    -1.76
    POSITIVE LOGITS
    fecture
    2.45
     countryside
    2.18
    Northern
    2.05
     populous
    1.95
     northern
    1.95
     battlefield
    1.95
     neigh
    1.94
     prosperous
    1.93
     Christmas
    1.92
     suburbs
    1.87
    Activations Density 0.000%

    No Known Activations