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. 2-ATT-KK
    6. 22431
    Prev
    Next
    INDEX
    Explanations

    lines of code or mathematical expressions, particularly focusing on variables and operators like assignments, increments, and comparisons

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    coding or programming-related terms and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.09
    2:0.05
    3:0.10
    4:0.04
    5:0.10
    6:0.09
    7:0.07
    8:0.07
    9:0.09
    10:0.13
    11:0.04
    Negative Logits
     negatively
    -1.24
    �
    -1.19
     adversely
    -1.10
    の�
    -1.08
    .""
    -1.07
    VII
    -1.07
     Parables
    -1.07
     urgently
    -1.07
     Hed
    -1.07
     tomorrow
    -1.06
    POSITIVE LOGITS
    password
    1.33
     rgb
    1.31
     Password
    1.28
     router
    1.25
     browsers
    1.25
    parser
    1.23
    gebra
    1.22
     parser
    1.22
     formatting
    1.22
     browser
    1.21
    Activations Density 0.010%

    No Known Activations