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. 9203
    Prev
    Next
    INDEX
    Explanations

    links and calls to action for social media engagement

    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
    0:0.06
    1:0.04
    2:0.03
    3:0.07
    4:0.05
    5:0.08
    6:0.10
    7:0.33
    8:0.06
    9:0.04
    10:0.03
    11:0.05
    Negative Logits
     dece
    -2.18
     exagger
    -2.10
     millisec
    -2.02
     recount
    -1.85
     illusion
    -1.78
     stripping
    -1.75
    adequ
    -1.75
    �
    -1.74
    PROV
    -1.72
     robbers
    -1.71
    POSITIVE LOGITS
     subscribe
    2.50
     Patreon
    2.48
     Subscribe
    2.39
     Email
    2.36
     Tune
    2.35
     email
    2.26
     Github
    2.26
     Contact
    2.26
     blogs
    2.25
    Subscribe
    2.25
    Activations Density 0.125%

    No Known Activations