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. 9-ATT-KK
    6. 65
    Prev
    Next
    INDEX
    Explanations

    positive and negative emotional states as well as concepts related to struggle and development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    2:0.06
    3:0.19
    4:0.03
    5:0.05
    6:0.01
    7:0.06
    8:0.03
    9:0.01
    10:0.39
    11:0.02
    Negative Logits
     Wrong
    -2.36
     correctly
    -2.21
     earlier
    -2.15
     definitively
    -2.11
    miah
    -2.10
    yrights
    -2.09
     properly
    -2.09
     originally
    -2.07
     incorrectly
    -2.06
     altogether
    -2.04
    POSITIVE LOGITS
     incess
    3.11
     constant
    3.05
     constantly
    3.00
     continual
    2.99
     bombard
    2.79
     relentless
    2.70
     nightly
    2.61
     reminders
    2.60
     continually
    2.60
     reminding
    2.57
    Activations Density 0.120%

    No Known Activations