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. 18904
    Prev
    Next
    INDEX
    Explanations

    specific types of nouns and their modifiers

    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
    0:0.40
    1:0.04
    2:0.04
    3:0.05
    4:0.07
    5:0.06
    6:0.06
    7:0.03
    8:0.07
    9:0.06
    10:0.03
    11:0.05
    Negative Logits
    iferation
    -2.04
    escription
    -1.94
     lecturer
    -1.93
     perpetrator
    -1.85
     narrator
    -1.84
     abuser
    -1.77
     counselor
    -1.76
    inventoryQuantity
    -1.68
     interviewer
    -1.67
     conductor
    -1.67
    POSITIVE LOGITS
    osc
    1.68
    EStreamFrame
    1.61
    abouts
    1.57
     Geh
    1.49
    cats
    1.47
     Compan
    1.44
    pas
    1.44
     Machines
    1.44
    fam
    1.44
    VM
    1.43
    Activations Density 0.001%

    No Known Activations