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. 5-ATT-KK
    6. 7258
    Prev
    Next
    INDEX
    Explanations

    phrases indicating blame or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.15
    3:0.05
    4:0.21
    5:0.02
    6:0.04
    7:0.19
    8:0.04
    9:0.03
    10:0.04
    11:0.14
    Negative Logits
    inventoryQuantity
    -1.38
     seriousness
    -1.34
     actionGroup
    -1.34
     decency
    -1.29
    odan
    -1.29
    urances
    -1.24
     simultane
    -1.19
    cookie
    -1.19
     disclaimer
    -1.17
    VOL
    -1.16
    POSITIVE LOGITS
     LH
    1.28
    ndum
    1.23
    minist
    1.15
    inic
    1.14
    owered
    1.14
     IST
    1.14
     SOM
    1.13
     Greenwich
    1.12
     Shining
    1.12
    lift
    1.12
    Activations Density 0.001%

    No Known Activations