© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10856
    Prev
    Next
    INDEX
    Explanations

    verbs related to attempts, failures, and actions involving obligations or permissions

    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
    1:0.06
    2:0.19
    3:0.05
    4:0.02
    5:0.02
    6:0.07
    7:0.25
    8:0.12
    9:0.02
    10:0.05
    11:0.07
    Negative Logits
     centrif
    -1.16
     Dh
    -1.15
    ioned
    -1.13
     Dull
    -1.10
     ¶
    -1.07
     Accessed
    -1.06
    lett
    -1.05
    charg
    -1.05
     Feder
    -1.03
     Converted
    -1.02
    POSITIVE LOGITS
     purposes
    1.72
     sake
    1.63
     reasons
    1.58
    ummies
    1.25
     offences
    1.16
     violations
    1.13
    payment
    1.11
     offenses
    1.10
    ancial
    1.10
     compliance
    1.09
    Activations Density 0.393%

    No Known Activations