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. 7733
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "an error has occurred."

    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
    0:0.36
    1:0.02
    2:0.07
    3:0.09
    4:0.04
    5:0.11
    6:0.02
    7:0.04
    8:0.06
    9:0.02
    10:0.08
    11:0.04
    Negative Logits
    adequ
    -2.33
     inadequate
    -2.26
     inadequ
    -2.13
     unfocused
    -2.12
     watered
    -2.12
     budgets
    -2.06
     dil
    -2.05
     mitigate
    -2.03
     insufficient
    -2.03
     arche
    -2.02
    POSITIVE LOGITS
     Login
    2.40
    print
    2.33
    spin
    2.23
     interception
    2.20
     crochet
    2.16
    gnu
    2.11
     cape
    2.11
     Kou
    2.09
     Cable
    2.08
     Gibbs
    2.07
    Activations Density 0.001%

    No Known Activations