© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 43416
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 't'

    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
    1:0.02
    2:0.29
    3:0.07
    4:0.06
    5:0.06
    6:0.10
    7:0.02
    8:0.09
    9:0.05
    10:0.05
    11:0.10
    Negative Logits
     Loaded
    -1.67
     Kafka
    -1.43
    iery
    -1.42
     Hits
    -1.42
     Story
    -1.38
    idation
    -1.32
    ography
    -1.28
    HQ
    -1.27
    resa
    -1.27
     Ku
    -1.26
    POSITIVE LOGITS
    orsi
    1.86
    owship
    1.77
    activate
    1.73
    etheless
    1.72
    rouse
    1.72
    viol
    1.65
    norm
    1.55
     recognize
    1.51
    luster
    1.50
    reon
    1.49
    Activations Density 0.053%

    No Known Activations