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. 5-ATT-KK
    6. 19362
    Prev
    Next
    INDEX
    Explanations

    the letter 't' in the text

    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
    0:0.05
    1:0.06
    2:0.07
    3:0.06
    4:0.11
    5:0.07
    6:0.06
    7:0.18
    8:0.05
    9:0.07
    10:0.07
    11:0.08
    Negative Logits
     perjury
    -1.41
     correctness
    -1.33
     separatist
    -1.30
     warfare
    -1.28
     Rahman
    -1.25
     certain
    -1.25
     rumors
    -1.24
    claimed
    -1.23
     outlaw
    -1.22
     insurgent
    -1.19
    POSITIVE LOGITS
    hetic
    1.49
    hift
    1.47
     diagram
    1.46
    inventoryQuantity
    1.44
    quickShipAvailable
    1.38
     concess
    1.34
    PLIED
    1.33
    yip
    1.33
    erity
    1.32
    lightly
    1.31
    Activations Density 0.000%

    No Known Activations