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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 44103
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to thoughts, opinions, and judgments on various subjects

    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
    1:0.02
    2:0.09
    3:0.14
    4:0.10
    5:0.06
    6:0.07
    7:0.06
    8:0.07
    9:0.07
    10:0.17
    11:0.08
    Negative Logits
    htaking
    -1.41
    ickets
    -1.38
    uters
    -1.32
    yip
    -1.27
    awks
    -1.24
    gypt
    -1.24
    zes
    -1.23
    ooked
    -1.21
     prest
    -1.21
    lycer
    -1.20
    POSITIVE LOGITS
     pursuits
    1.49
     accomplishments
    1.46
     progress
    1.40
     endeavors
    1.39
     faithfully
    1.33
     status
    1.29
     duties
    1.28
     accordingly
    1.28
     philosophy
    1.27
     exploits
    1.26
    Activations Density 0.123%

    No Known Activations