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. 5-ATT-KK
    6. 2818
    Prev
    Next
    INDEX
    Explanations

    references to significant statistics or data points related to specific topics

    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
    0:0.02
    1:0.02
    2:0.17
    3:0.12
    4:0.22
    5:0.05
    6:0.06
    7:0.03
    8:0.05
    9:0.10
    10:0.07
    11:0.04
    Negative Logits
     Paraly
    -1.50
     Sting
    -1.45
     [*
    -1.37
     appar
    -1.31
     Fle
    -1.29
     Cure
    -1.29
     Guinness
    -1.27
     Stretch
    -1.20
     Pact
    -1.19
     Cyr
    -1.18
    POSITIVE LOGITS
    malink
    2.04
    imeo
    1.78
    "]=>
    1.66
    tnc
    1.64
    elaide
    1.44
    topic
    1.42
    iland
    1.42
    ゼウス
    1.42
    inion
    1.42
    ]:
    1.41
    Activations Density 0.026%

    No Known Activations