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. 7-ATT-KK
    6. 9097
    Prev
    Next
    INDEX
    Explanations

    instances of the word "go."

    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
    0:0.07
    1:0.09
    2:0.07
    3:0.07
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.09
    9:0.09
    10:0.06
    11:0.09
    Negative Logits
    eland
    -2.29
    ogue
    -2.25
    century
    -2.25
    democratic
    -2.23
    occup
    -2.23
    civil
    -2.20
    alyses
    -2.19
    ceptive
    -2.17
    danger
    -2.17
    espie
    -2.13
    POSITIVE LOGITS
     Loot
    2.24
     Animation
    2.19
     Cance
    2.18
     Creatures
    2.07
    selage
    2.06
     Tape
    2.05
     Spo
    1.98
     Casting
    1.93
    Actor
    1.88
     Inventory
    1.87
    Activations Density 0.000%

    No Known Activations