Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44305
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "you."

    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
    1:0.01
    2:0.20
    3:0.12
    4:0.15
    5:0.03
    6:0.14
    7:0.09
    8:0.03
    9:0.05
    10:0.07
    11:0.03
    Negative Logits
    sbm
    -1.80
    emale
    -1.59
    ruary
    -1.52
     lobb
    -1.51
     alike
    -1.49
     respectively
    -1.47
    oglu
    -1.42
    gged
    -1.40
    pole
    -1.38
    eder
    -1.36
    POSITIVE LOGITS
     ILCS
    1.52
    Latin
    1.38
    library
    1.38
    currency
    1.37
    Break
    1.32
     trivia
    1.28
     calib
    1.25
     scarce
    1.25
    Breaking
    1.22
     clarity
    1.22
    Activations Density 0.000%

    No Known Activations