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. 3169
    Prev
    Next
    INDEX
    Explanations

    phrases related to rankings or comparisons

    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
    0:0.06
    1:0.19
    2:0.06
    3:0.06
    4:0.05
    5:0.04
    6:0.16
    7:0.05
    8:0.03
    9:0.18
    10:0.03
    11:0.04
    Negative Logits
     Idle
    -3.57
     Dy
    -3.52
     Dog
    -3.44
     Jere
    -3.29
     Doc
    -2.94
     Ging
    -2.94
     Huff
    -2.89
     pid
    -2.83
    tick
    -2.77
     Crow
    -2.75
    POSITIVE LOGITS
    large
    4.08
    Large
    3.79
    emale
    3.38
     Large
    3.26
     Carl
    3.04
     large
    2.98
    ucle
    2.98
    Carl
    2.96
    aucas
    2.91
    arger
    2.89
    Activations Density 0.001%

    No Known Activations