© 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. 10-ATT-KK
    11. 14431
    Prev
    Next
    INDEX
    Explanations

    phrases associated with highs and lows in experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.20
    2:0.03
    3:0.07
    4:0.09
    5:0.03
    6:0.04
    7:0.14
    8:0.03
    9:0.05
    10:0.04
    11:0.20
    Negative Logits
    ovember
    -2.61
     Minute
    -2.58
    BUG
    -2.26
     Mercy
    -2.25
    ^^
    -2.21
     arrang
    -2.20
    handler
    -2.18
     Instruction
    -2.14
     FAC
    -2.12
     excuse
    -2.10
    POSITIVE LOGITS
     highs
    4.84
     lows
    4.59
     peaks
    3.30
    inventoryQuantity
    3.25
     negatives
    3.11
     heights
    3.11
     extremes
    2.87
     bumps
    2.85
     ceilings
    2.76
    20439
    2.75
    Activations Density 0.000%

    No Known Activations