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. 44338
    Prev
    Next
    INDEX
    Explanations

    complex concepts related to social or political issues and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.02
    2:0.32
    3:0.09
    4:0.10
    5:0.03
    6:0.08
    7:0.10
    8:0.04
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
    ories
    -2.12
    oppers
    -1.82
    tops
    -1.82
     Tycoon
    -1.78
    assies
    -1.76
    Reviewed
    -1.75
     Tags
    -1.73
    ategories
    -1.71
    lees
    -1.71
    ctors
    -1.70
    POSITIVE LOGITS
     adversary
    1.71
     named
    1.69
     consisting
    1.68
    dylib
    1.60
    emphasis
    1.58
    ENSE
    1.48
     proposition
    1.46
     punct
    1.45
     vulnerability
    1.44
     attitude
    1.43
    Activations Density 0.273%

    No Known Activations