Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3034
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology and engineering solutions in industrial and healthcare 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
    0:0.05
    1:0.02
    2:0.09
    3:0.20
    4:0.06
    5:0.08
    6:0.02
    7:0.03
    8:0.07
    9:0.10
    10:0.14
    11:0.10
    Negative Logits
    )?
    -2.21
    ?),
    -2.07
    ?).
    -1.89
     Presumably
    -1.82
    Answer
    -1.77
    .):
    -1.76
     Suppose
    -1.66
    ?)
    -1.63
     Anyway
    -1.61
    ?:
    -1.59
    POSITIVE LOGITS
     innovative
    2.00
     sculpt
    1.70
     seamlessly
    1.66
     blending
    1.64
     innov
    1.62
     vibrant
    1.62
     timeless
    1.61
     puls
    1.60
     versatile
    1.58
     stylish
    1.56
    Activations Density 0.301%

    No Known Activations