© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 35332
    Prev
    Next
    INDEX
    Explanations

    phrases related to probabilities and chances of events occurring

    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
    0:0.03
    1:0.03
    2:0.13
    3:0.07
    4:0.10
    5:0.03
    6:0.06
    7:0.31
    8:0.02
    9:0.03
    10:0.07
    11:0.07
    Negative Logits
    izons
    -1.66
    ourage
    -1.63
    ylum
    -1.61
    inventoryQuantity
    -1.48
    terday
    -1.45
    minus
    -1.44
     GOODMAN
    -1.39
    rupulous
    -1.37
    BuyableInstoreAndOnline
    -1.37
    flies
    -1.34
    POSITIVE LOGITS
     occurrence
    1.68
     outcome
    1.53
     interpol
    1.44
    Delete
    1.38
     inacc
    1.37
     pron
    1.36
     deletion
    1.34
    RECT
    1.34
     misinterpret
    1.34
    Result
    1.33
    Activations Density 0.002%

    No Known Activations