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. 7-ATT-KK
    6. 8961
    Prev
    Next
    INDEX
    Explanations

    statistical information related to rankings and performance metrics in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.06
    2:0.03
    3:0.07
    4:0.07
    5:0.15
    6:0.18
    7:0.08
    8:0.08
    9:0.03
    10:0.04
    11:0.07
    Negative Logits
    merce
    -2.17
    ombat
    -2.15
    Explore
    -1.98
    redients
    -1.97
     subscription
    -1.96
     Annotations
    -1.93
     ebook
    -1.88
     cubes
    -1.88
     attachments
    -1.86
     membership
    -1.81
    POSITIVE LOGITS
    Weak
    2.09
     Outs
    2.09
     Passing
    2.03
     Defensive
    1.99
    akable
    1.99
     dominant
    1.93
     Stadium
    1.92
    Strong
    1.86
     Percentage
    1.86
    Against
    1.86
    Activations Density 0.013%

    No Known Activations