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. 8924
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the importance and authority of a topic

    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
    0:0.05
    1:0.09
    2:0.01
    3:0.17
    4:0.05
    5:0.10
    6:0.08
    7:0.05
    8:0.12
    9:0.17
    10:0.03
    11:0.03
    Negative Logits
    wik
    -1.87
     Franch
    -1.72
     belts
    -1.71
    outhern
    -1.67
    trak
    -1.64
    agna
    -1.62
     Sno
    -1.61
     vans
    -1.58
    ntil
    -1.56
    phal
    -1.55
    POSITIVE LOGITS
     subsequently
    2.10
     beforehand
    2.07
     ensuing
    2.06
     accordingly
    2.06
     subsequent
    2.04
     desired
    1.98
     afterward
    1.97
    ────
    1.92
     predetermined
    1.90
     intervening
    1.88
    Activations Density 0.759%

    No Known Activations