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. 3-ATT-KK
    6. 8420
    Prev
    Next
    INDEX
    Explanations

    phrases indicating diversion or redirection of resources or attention

    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
    0:0.01
    1:0.03
    2:0.06
    3:0.08
    4:0.01
    5:0.04
    6:0.05
    7:0.09
    8:0.08
    9:0.28
    10:0.06
    11:0.15
    Negative Logits
    arella
    -1.09
    Optional
    -1.08
     Walk
    -1.07
    KY
    -1.05
    Supported
    -1.01
    optional
    -1.00
     citiz
    -0.97
    Multi
    -0.97
    Afee
    -0.97
     necklace
    -0.96
    POSITIVE LOGITS
    ocus
    1.22
    href
    1.19
    gency
    1.18
     overboard
    1.15
     focus
    1.13
     focusing
    1.11
    ierre
    1.11
     overd
    1.09
    sic
    1.08
    channelAvailability
    1.06
    Activations Density 0.005%

    No Known Activations