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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9478
    Prev
    Next
    INDEX
    Explanations

    references to space exploration and scientific advancements

    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
    0:0.15
    1:0.06
    2:0.05
    3:0.08
    4:0.06
    5:0.18
    6:0.15
    7:0.03
    8:0.06
    9:0.09
    10:0.02
    11:0.02
    Negative Logits
     Grimoire
    -2.14
     macros
    -2.06
     OCD
    -2.05
     Reincarn
    -2.03
     Leilan
    -1.90
     traps
    -1.86
    BILITIES
    -1.85
     Curse
    -1.83
     Persona
    -1.82
    ¶
    -1.82
    POSITIVE LOGITS
    ONSORED
    2.81
    hello
    2.66
    Trend
    2.32
    News
    2.31
    alon
    2.22
    ernand
    2.03
    thouse
    2.02
    LOS
    2.02
    utterstock
    2.01
    iminary
    1.98
    Activations Density 0.132%

    No Known Activations