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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44231
    Prev
    Next
    INDEX
    Explanations

    labels related to visual content formats like galleries and thumbnails

    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
    2:0.07
    3:0.09
    4:0.06
    5:0.07
    6:0.08
    7:0.20
    8:0.08
    9:0.07
    10:0.07
    11:0.09
    Negative Logits
     Trave
    -1.69
     Powell
    -1.56
     ageing
    -1.53
     Mandal
    -1.41
     anthropology
    -1.40
     domest
    -1.37
     ming
    -1.33
     ethnicity
    -1.33
     Morg
    -1.32
     Bauer
    -1.30
    POSITIVE LOGITS
    interstitial
    1.84
    Reviewer
    1.65
    COMPLE
    1.64
     captcha
    1.55
    ean
    1.55
    ']
    1.54
    chan
    1.53
    rection
    1.49
     orbit
    1.49
    illary
    1.43
    Activations Density 0.001%

    No Known Activations