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. 7-ATT-KK
    6. 8959
    Prev
    Next
    INDEX
    Explanations

    commands or imperatives in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    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
    1:0.08
    2:0.08
    3:0.10
    4:0.08
    5:0.08
    6:0.07
    7:0.08
    8:0.07
    9:0.08
    10:0.08
    11:0.06
    Negative Logits
    phabet
    -2.65
    vernment
    -2.64
     actionGroup
    -2.43
    partisan
    -2.42
    andom
    -2.38
    population
    -2.36
    oyal
    -2.35
    incial
    -2.35
    parency
    -2.29
    VIDIA
    -2.27
    POSITIVE LOGITS
     Horowitz
    2.22
     postp
    2.18
     OK
    2.10
     argued
    2.08
     accidentally
    2.02
     Butt
    2.02
     Kuh
    2.01
     SQ
    1.99
     Coffin
    1.95
     Fig
    1.92
    Activations Density 0.000%

    No Known Activations