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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7877
    Prev
    Next
    INDEX
    Explanations

    references to domain names and web addresses

    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
    0:0.28
    1:0.04
    2:0.08
    3:0.07
    4:0.09
    5:0.04
    6:0.05
    7:0.08
    8:0.05
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
    eatures
    -1.32
     plaintiffs
    -1.14
     Ambro
    -1.12
    lement
    -1.11
     mathematician
    -1.09
    icularly
    -1.05
    ishable
    -1.05
     surpr
    -1.03
     plaintiff
    -1.01
    iously
    -1.01
    POSITIVE LOGITS
     Ltd
    1.34
    udeb
    1.30
    hare
    1.29
    Ops
    1.28
    esa
    1.25
    bleacher
    1.24
    tein
    1.23
    cko
    1.22
     Advisor
    1.21
    opa
    1.20
    Activations Density 0.024%

    No Known Activations