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. 5-ATT-KK
    6. 27593
    Prev
    Next
    INDEX
    Explanations

    statistical figures and performance metrics related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.03
    2:0.12
    3:0.03
    4:0.05
    5:0.10
    6:0.03
    7:0.02
    8:0.30
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
    gif
    -1.61
    Reviewer
    -1.56
    omy
    -1.52
    otation
    -1.45
    angelo
    -1.44
     remod
    -1.42
    rollers
    -1.41
    ゴン
    -1.41
     rehe
    -1.37
    mony
    -1.37
    POSITIVE LOGITS
    +=
    1.68
    aucuses
    1.68
     respectively
    1.63
    ++)
    1.50
     +=
    1.45
    +.
    1.44
     AVG
    1.44
    ++
    1.38
    anian
    1.35
    daq
    1.34
    Activations Density 0.082%

    No Known Activations