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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 14014
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals being behind bars

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.09
    1:0.01
    2:0.34
    3:0.09
    4:0.06
    5:0.09
    6:0.02
    7:0.02
    8:0.11
    9:0.07
    10:0.03
    11:0.02
    Negative Logits
    nces
    -1.08
     glim
    -1.06
     alum
    -1.05
    nect
    -1.03
     Soup
    -1.01
    bach
    -1.01
    sym
    -1.01
     expert
    -1.00
     Qiao
    -0.99
     Vance
    -0.94
    POSITIVE LOGITS
     borders
    1.27
     horizon
    1.22
    _.
    1.22
    riot
    1.19
    tty
    1.19
    laughs
    1.18
    士
    1.16
     walls
    1.13
    Laughs
    1.10
     ears
    1.09
    Activations Density 0.027%

    No Known Activations