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. 9-ATT-KK
    6. 36
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and statistics, especially in structured formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.55
    2:0.02
    3:0.03
    4:0.03
    5:0.06
    6:0.06
    7:0.04
    8:0.02
    9:0.07
    10:0.03
    11:0.03
    Negative Logits
    ateurs
    -3.21
    �
    -3.06
    llah
    -2.93
    cgi
    -2.87
    baugh
    -2.86
    glers
    -2.81
    heit
    -2.79
    plex
    -2.77
    hower
    -2.72
    rils
    -2.69
    POSITIVE LOGITS
     14
    4.40
    14
    4.38
     13
    3.72
    13
    3.66
     1400
    3.53
     fourteen
    3.16
     15
    3.09
    15
    3.05
    143
    3.03
     1440
    2.99
    Activations Density 0.032%

    No Known Activations