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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 22385
    Prev
    Next
    INDEX
    Explanations

    organizations and individuals involved in events or activities, potentially related to politics and legal matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    occurrences of the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.06
    1:0.03
    2:0.05
    3:0.04
    4:0.06
    5:0.06
    6:0.07
    7:0.16
    8:0.04
    9:0.05
    10:0.22
    11:0.11
    Negative Logits
    Reviewer
    -0.62
     whereas
    -0.59
     notwithstanding
    -0.59
     net
    -0.58
    -[
    -0.56
    FTWARE
    -0.56
     Niet
    -0.56
     Blueprint
    -0.55
     Fresh
    -0.55
     Blues
    -0.54
    POSITIVE LOGITS
    pees
    0.82
    fect
    0.74
    lations
    0.73
    agog
    0.72
    azeera
    0.71
    geries
    0.70
    viron
    0.69
    cemic
    0.68
    ribe
    0.68
     neighb
    0.67
    Activations Density 0.322%

    No Known Activations