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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10554
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions in complex sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.19
    3:0.03
    4:0.03
    5:0.05
    6:0.12
    7:0.13
    8:0.07
    9:0.04
    10:0.15
    11:0.09
    Negative Logits
    ffic
    -1.38
    Premium
    -1.17
    jriwal
    -1.15
     Pyr
    -1.12
    パ
    -1.07
    cellent
    -1.06
    rite
    -1.06
     Cloud
    -1.05
     ®
    -1.04
     GF
    -1.03
    POSITIVE LOGITS
    maxwell
    1.15
    bilt
    1.11
     adolesc
    1.06
    isSpecialOrderable
    1.05
     arrivals
    1.04
    cigarette
    1.04
    zag
    0.99
    ource
    0.98
     JOHN
    0.98
     victimized
    0.97
    Activations Density 0.030%

    No Known Activations