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. 9600
    Prev
    Next
    INDEX
    Explanations

    references to legal or judicial proceedings

    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
    0:0.07
    1:0.05
    2:0.01
    3:0.05
    4:0.05
    5:0.07
    6:0.04
    7:0.03
    8:0.44
    9:0.06
    10:0.02
    11:0.04
    Negative Logits
    cia
    -2.12
    lov
    -1.92
    href
    -1.66
    QL
    -1.65
    viol
    -1.65
    aka
    -1.62
    mania
    -1.60
    malink
    -1.57
    future
    -1.56
    iku
    -1.54
    POSITIVE LOGITS
     assembled
    1.75
     stacked
    1.71
    20439
    1.60
    ixty
    1.59
     Gallagher
    1.59
    cise
    1.58
     Aires
    1.52
     Mori
    1.47
    arial
    1.45
     claw
    1.42
    Activations Density 0.000%

    No Known Activations