© 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. 2-ATT-KK
    6. 22965
    Prev
    Next
    INDEX
    Explanations

    names of characters from superhero movies and comics

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

    content related to comic book characters and their affiliations within the Marvel and DC universes

    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
    3:0.05
    4:0.03
    5:0.07
    6:0.07
    7:0.12
    8:0.05
    9:0.11
    10:0.16
    11:0.08
    Negative Logits
     informal
    -1.24
     administrative
    -1.17
     econom
    -1.16
     university
    -1.13
     vocational
    -1.13
     NGO
    -1.12
     education
    -1.11
     unemploy
    -1.09
     Applicant
    -1.07
     administr
    -1.06
    POSITIVE LOGITS
     sequels
    1.59
     Deadpool
    1.46
    Batman
    1.37
    Marvel
    1.36
     Dracula
    1.35
    Spoiler
    1.32
    antasy
    1.29
     trilogy
    1.24
    Blade
    1.24
    canon
    1.23
    Activations Density 0.201%

    No Known Activations