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. 7-ATT-KK
    6. 9524
    Prev
    Next
    INDEX
    Explanations

    references to concealed carry permits and assistance given to others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.09
    2:0.16
    3:0.03
    4:0.02
    5:0.03
    6:0.05
    7:0.07
    8:0.03
    9:0.04
    10:0.34
    11:0.04
    Negative Logits
    Graph
    -2.54
    Stars
    -2.37
    iak
    -2.25
     ge
    -2.17
     Geological
    -2.13
    Ge
    -2.07
    wall
    -2.07
    escription
    -2.06
    enburg
    -2.03
    Ec
    -2.02
    POSITIVE LOGITS
     carry
    3.94
     carrying
    3.78
     Carry
    3.66
    carry
    3.42
     carried
    3.17
     carries
    3.12
     carrier
    2.70
     holder
    2.52
     Clare
    2.44
     carriers
    2.37
    Activations Density 0.001%

    No Known Activations