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. 11450
    Prev
    Next
    INDEX
    Explanations

    references to requests for comments or updates regarding various topics

    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
    1:0.03
    2:0.11
    3:0.09
    4:0.13
    5:0.10
    6:0.04
    7:0.20
    8:0.04
    9:0.04
    10:0.08
    11:0.04
    Negative Logits
    uddenly
    -2.29
     converge
    -2.26
     resil
    -2.21
     mobs
    -2.10
     experien
    -2.08
     sacrific
    -2.07
     fortun
    -2.04
     gradual
    -2.01
     mirac
    -1.95
     palms
    -1.94
    POSITIVE LOGITS
     spokesperson
    2.95
    Asked
    2.78
     spokeswoman
    2.76
    Sources
    2.66
    Update
    2.65
     spokesman
    2.51
     TBD
    2.49
    UPDATE
    2.43
     Asked
    2.39
    Discuss
    2.38
    Activations Density 0.151%

    No Known Activations