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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 7628
    Prev
    Next
    INDEX
    Explanations

    indicators related to rankings and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.29
    2:0.03
    3:0.06
    4:0.02
    5:0.06
    6:0.12
    7:0.05
    8:0.02
    9:0.16
    10:0.03
    11:0.08
    Negative Logits
     guiActiveUn
    -3.10
    ��
    -2.96
    */(
    -2.96
    erity
    -2.77
    tw
    -2.75
    pora
    -2.74
    pes
    -2.69
    FTWARE
    -2.66
    >:
    -2.64
    mr
    -2.58
    POSITIVE LOGITS
     overall
    5.45
     Overall
    4.67
    Overall
    4.15
     individually
    3.51
     general
    3.46
    general
    3.05
     ultimately
    2.98
     really
    2.94
     definitely
    2.90
     otherwise
    2.88
    Activations Density 0.002%

    No Known Activations