Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22276
    Prev
    Next
    INDEX
    Explanations

    references to specific versions of the Internet Explorer browser

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.06
    2:0.16
    3:0.11
    4:0.13
    5:0.04
    6:0.04
    7:0.04
    8:0.04
    9:0.15
    10:0.07
    11:0.04
    Negative Logits
    foreseen
    -1.46
    anie
    -1.36
     Osw
    -1.27
    aughter
    -1.26
     bond
    -1.25
    aughters
    -1.24
    inqu
    -1.23
    orah
    -1.22
    charged
    -1.20
    EStreamFrame
    -1.19
    POSITIVE LOGITS
     Digest
    1.73
     Phantom
    1.57
    DOM
    1.31
    merce
    1.31
    JS
    1.28
     Launch
    1.24
     Egyptians
    1.19
     LD
    1.18
     Decoder
    1.17
     Odyssey
    1.16
    Activations Density 0.003%

    No Known Activations