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. 10210
    Prev
    Next
    INDEX
    Explanations

    references to specific intersections and locations

    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
    0:0.01
    1:0.06
    2:0.07
    3:0.05
    4:0.03
    5:0.05
    6:0.06
    7:0.08
    8:0.11
    9:0.06
    10:0.06
    11:0.30
    Negative Logits
     manip
    -1.24
    =-=-=-=-
    -1.15
     effic
    -1.13
     complicit
    -1.12
     sacrifices
    -1.12
     manipulated
    -1.11
     projections
    -1.11
     pressured
    -1.11
     largeDownload
    -1.10
     manipulative
    -1.08
    POSITIVE LOGITS
    augh
    1.26
    ansas
    1.23
    idian
    1.22
    rium
    1.22
     Golf
    1.22
    town
    1.21
    Sax
    1.20
     Coffee
    1.20
     js
    1.19
    pg
    1.17
    Activations Density 0.011%

    No Known Activations