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. 3059
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" across different contexts

    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
    0:0.17
    1:0.02
    2:0.15
    3:0.14
    4:0.04
    5:0.08
    6:0.04
    7:0.04
    8:0.11
    9:0.04
    10:0.03
    11:0.09
    Negative Logits
     Turk
    -1.74
    Fin
    -1.73
    Kin
    -1.73
    CTV
    -1.72
    ylan
    -1.70
    Pen
    -1.64
    Pol
    -1.64
    Face
    -1.63
    tro
    -1.62
    mob
    -1.61
    POSITIVE LOGITS
    versely
    1.59
    olean
    1.57
     ppm
    1.54
    ivably
    1.48
     Mahjong
    1.46
     undecided
    1.45
     unfocusedRange
    1.44
     desired
    1.43
     qual
    1.41
     indeed
    1.40
    Activations Density 0.003%

    No Known Activations