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. 9385
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their affiliations or roles

    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
    0:0.10
    1:0.04
    2:0.03
    3:0.07
    4:0.07
    5:0.18
    6:0.09
    7:0.02
    8:0.17
    9:0.10
    10:0.01
    11:0.07
    Negative Logits
     sacrifices
    -1.76
     nudity
    -1.75
     achieves
    -1.74
     pics
    -1.73
    etheless
    -1.72
     dramas
    -1.68
     ideals
    -1.68
     disrespect
    -1.68
     subjug
    -1.67
     deval
    -1.67
    POSITIVE LOGITS
    Senior
    2.10
    doctoral
    2.04
     Associate
    2.01
     Fellow
    1.97
     consultant
    1.96
    ector
    1.95
     Forensic
    1.95
    director
    1.94
     Assistant
    1.92
     Associates
    1.91
    Activations Density 0.037%

    No Known Activations