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. 7565
    Prev
    Next
    INDEX
    Explanations

    the letter "J"

    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
    0:0.10
    1:0.08
    2:0.07
    3:0.08
    4:0.08
    5:0.07
    6:0.08
    7:0.07
    8:0.08
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    advant
    -2.98
    JC
    -2.89
    adra
    -2.78
    jee
    -2.77
    jun
    -2.73
    ARC
    -2.67
    Sah
    -2.67
    Jose
    -2.66
    Fax
    -2.56
    apses
    -2.56
    POSITIVE LOGITS
     Hook
    2.99
     Rider
    2.95
     Thorn
    2.90
     Lank
    2.59
     Whe
    2.55
     Zup
    2.52
     Logan
    2.47
     Wh
    2.44
     responsiveness
    2.42
     complied
    2.41
    Activations Density 0.000%

    No Known Activations