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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 44281
    Prev
    Next
    INDEX
    Explanations

    statistical values related to performance metrics in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.05
    1:0.03
    2:0.08
    3:0.04
    4:0.07
    5:0.04
    6:0.36
    7:0.06
    8:0.07
    9:0.04
    10:0.07
    11:0.04
    Negative Logits
    lain
    -1.40
    arger
    -1.26
    oples
    -1.21
     hy
    -1.21
    NetMessage
    -1.20
    Haunted
    -1.18
    ��
    -1.18
    achine
    -1.17
    Tea
    -1.17
     PATH
    -1.16
    POSITIVE LOGITS
    minus
    1.75
     coefficient
    1.51
     minus
    1.50
    neau
    1.49
     Ake
    1.39
    /+
    1.31
     coefficients
    1.29
    fee
    1.27
    hetti
    1.27
    onential
    1.26
    Activations Density 0.004%

    No Known Activations