© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43248
    Prev
    Next
    INDEX
    Explanations

    instances of the word "alone."

    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
    0:0.02
    1:0.03
    2:0.16
    3:0.06
    4:0.11
    5:0.03
    6:0.05
    7:0.04
    8:0.12
    9:0.04
    10:0.06
    11:0.24
    Negative Logits
    CTV
    -1.92
    DragonMagazine
    -1.78
    MET
    -1.70
     HBO
    -1.66
     CGI
    -1.62
     Cortana
    -1.61
     Pand
    -1.60
     Hancock
    -1.57
     Raw
    -1.57
     aeros
    -1.56
    POSITIVE LOGITS
    ilaterally
    2.20
    ntil
    1.95
    iculty
    1.88
     impede
    1.87
    orgetown
    1.85
     insure
    1.74
    rupt
    1.73
    idable
    1.73
    locking
    1.68
    locks
    1.68
    Activations Density 0.001%

    No Known Activations