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. 9-ATT-KK
    6. 7748
    Prev
    Next
    INDEX
    Explanations

    mentions of specific brands or titles within the text

    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
    1:0.12
    2:0.10
    3:0.05
    4:0.05
    5:0.05
    6:0.16
    7:0.04
    8:0.03
    9:0.23
    10:0.03
    11:0.02
    Negative Logits
     Rose
    -3.25
     MJ
    -3.06
    EY
    -3.02
     Anthony
    -2.94
     Phoenix
    -2.93
     Por
    -2.93
     Seymour
    -2.87
    yt
    -2.83
     445
    -2.81
    Phoenix
    -2.79
    POSITIVE LOGITS
    limit
    6.32
     limit
    5.40
    Limit
    5.31
    limits
    5.18
     limits
    5.12
     Limit
    4.96
     Limits
    4.58
    Lim
    4.43
     restriction
    4.37
     Restrict
    4.29
    Activations Density 0.004%

    No Known Activations