© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22833
    Prev
    Next
    INDEX
    Explanations

    mentions of specific years or time periods

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

    mentions of time and duration in various contexts

    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
    0:0.07
    1:0.02
    2:0.18
    3:0.06
    4:0.24
    5:0.07
    6:0.06
    7:0.01
    8:0.08
    9:0.07
    10:0.06
    11:0.03
    Negative Logits
    ocent
    -1.47
     Unch
    -1.33
     Malt
    -1.30
    ��
    -1.25
    nce
    -1.23
    uming
    -1.20
     Levant
    -1.20
    Normal
    -1.20
     Past
    -1.20
     Reson
    -1.19
    POSITIVE LOGITS
     portfolios
    1.47
     acron
    1.40
    dozen
    1.38
     favourites
    1.36
    factor
    1.36
     studios
    1.35
    prises
    1.34
     continents
    1.33
     cartridges
    1.31
    abyte
    1.31
    Activations Density 0.037%

    No Known Activations