© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 44034
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "t" and its variations in different contexts

    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
    0:0.04
    1:0.03
    2:0.25
    3:0.05
    4:0.07
    5:0.04
    6:0.23
    7:0.03
    8:0.04
    9:0.03
    10:0.05
    11:0.07
    Negative Logits
     Pil
    -1.40
    Topics
    -1.38
     captcha
    -1.38
     Kom
    -1.32
     Sut
    -1.32
    fixes
    -1.30
     combines
    -1.30
    版
    -1.28
     Daw
    -1.25
    chin
    -1.25
    POSITIVE LOGITS
    eem
    1.67
    atown
    1.64
    versible
    1.60
    enough
    1.59
    NULL
    1.56
     agre
    1.55
    icted
    1.54
    ivable
    1.54
     sshd
    1.53
     anymore
    1.50
    Activations Density 0.026%

    No Known Activations