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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19354
    Prev
    Next
    INDEX
    Explanations

    statements expressing skepticism or doubt about claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.03
    1:0.04
    2:0.23
    3:0.08
    4:0.11
    5:0.03
    6:0.06
    7:0.15
    8:0.04
    9:0.06
    10:0.07
    11:0.05
    Negative Logits
    orian
    -1.75
     versus
    -1.66
    emi
    -1.58
    ocr
    -1.56
     background
    -1.47
     Awakens
    -1.47
    ocracy
    -1.47
    oran
    -1.44
    arkin
    -1.40
    ocratic
    -1.39
    POSITIVE LOGITS
    UGC
    1.44
    theless
    1.42
     Guilty
    1.39
     Breach
    1.35
    gans
    1.35
    CLASS
    1.34
    ⓘ
    1.33
    saf
    1.33
    WHERE
    1.32
    mpeg
    1.31
    Activations Density 0.001%

    No Known Activations