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. 2-ATT-KK
    6. 13957
    Prev
    Next
    INDEX
    Explanations

    phrases related to return on investment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.04
    3:0.05
    4:0.39
    5:0.07
    6:0.02
    7:0.01
    8:0.10
    9:0.09
    10:0.05
    11:0.02
    Negative Logits
    acci
    -1.51
    nect
    -1.45
    andowski
    -1.43
    atin
    -1.40
    kered
    -1.38
    uthor
    -1.38
    ritical
    -1.37
    ister
    -1.33
    ombs
    -1.33
    icago
    -1.32
    POSITIVE LOGITS
    Returns
    1.48
     obscurity
    1.39
    Adds
    1.36
     parity
    1.35
     civilisation
    1.34
     riches
    1.29
     Rece
    1.27
    Buyable
    1.26
     heights
    1.25
     novelty
    1.24
    Activations Density 0.012%

    No Known Activations