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. 3150
    Prev
    Next
    INDEX
    Explanations

    statistical comparisons and rankings

    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
    1:0.02
    2:0.07
    3:0.08
    4:0.06
    5:0.03
    6:0.03
    7:0.05
    8:0.05
    9:0.07
    10:0.39
    11:0.08
    Negative Logits
    bleacher
    -1.91
    ollah
    -1.88
    iot
    -1.76
    ulk
    -1.75
     grievances
    -1.67
    aunders
    -1.65
     interfere
    -1.64
    wr
    -1.64
    ontent
    -1.63
    oldown
    -1.59
    POSITIVE LOGITS
     Grande
    1.91
     Trends
    1.77
     whopping
    1.75
     nominations
    1.68
    wcsstore
    1.67
    ゼウス
    1.67
    isSpecialOrderable
    1.62
     genus
    1.61
    SELECT
    1.57
    Ping
    1.56
    Activations Density 0.169%

    No Known Activations