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. 7-ATT-KK
    6. 9121
    Prev
    Next
    INDEX
    Explanations

    research publication details and metadata

    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
    0:0.12
    1:0.01
    2:0.01
    3:0.08
    4:0.11
    5:0.22
    6:0.03
    7:0.00
    8:0.18
    9:0.17
    10:0.01
    11:0.01
    Negative Logits
     Archdemon
    -1.92
     racks
    -1.90
     averaging
    -1.78
    yip
    -1.77
     chanting
    -1.77
     caster
    -1.75
     photographers
    -1.75
     spraying
    -1.72
     Alchemy
    -1.70
     DJs
    -1.69
    POSITIVE LOGITS
    stad
    2.12
    tx
    2.08
    mur
    2.00
    file
    1.94
    tre
    1.89
    avin
    1.86
    vez
    1.85
    RAW
    1.82
    romy
    1.81
    osal
    1.80
    Activations Density 0.002%

    No Known Activations