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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10215
    Prev
    Next
    INDEX
    Explanations

    words that suggest positivity or favorable conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.04
    2:0.08
    3:0.33
    4:0.03
    5:0.02
    6:0.08
    7:0.10
    8:0.04
    9:0.06
    10:0.07
    11:0.07
    Negative Logits
    pole
    -1.29
    Bir
    -1.19
    Password
    -1.13
    otide
    -1.13
    chip
    -1.12
    assetsadobe
    -1.05
    agos
    -1.04
    IFF
    -1.03
    Spider
    -1.02
    Pref
    -1.01
    POSITIVE LOGITS
    lishes
    1.37
     Mormonism
    1.28
     Mormons
    1.20
    emonium
    1.10
     Klu
    1.09
     BYU
    1.09
    ctory
    1.08
    ilst
    1.08
    redients
    1.06
    ESE
    1.04
    Activations Density 0.004%

    No Known Activations