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. 9575
    Prev
    Next
    INDEX
    Explanations

    the action of movement or direction

    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
    0:0.09
    1:0.06
    2:0.06
    3:0.08
    4:0.08
    5:0.07
    6:0.07
    7:0.07
    8:0.09
    9:0.08
    10:0.09
    11:0.09
    Negative Logits
     roy
    -2.24
     Nasa
    -2.22
     royal
    -2.15
     Carbuncle
    -2.07
     tha
    -2.02
     nud
    -2.00
     palace
    -1.99
     Genie
    -1.96
     Ain
    -1.95
     Merlin
    -1.95
    POSITIVE LOGITS
    verages
    2.76
    otta
    2.68
    Civil
    2.52
    seless
    2.33
    ufact
    2.32
    limited
    2.24
    itte
    2.23
    integ
    2.20
    ensable
    2.20
    Heavy
    2.19
    Activations Density 0.000%

    No Known Activations