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. 22257
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes or actions that require a sequence or precondition

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.04
    1:0.03
    2:0.04
    3:0.05
    4:0.21
    5:0.08
    6:0.04
    7:0.09
    8:0.09
    9:0.08
    10:0.13
    11:0.07
    Negative Logits
    mouth
    -1.20
     Lemon
    -1.18
    worm
    -1.14
     Lun
    -1.07
     stump
    -1.06
     Pow
    -1.04
    bill
    -1.03
    acid
    -1.02
    burgh
    -1.02
    gee
    -1.02
    POSITIVE LOGITS
    otiation
    1.39
    izo
    1.23
    hetics
    1.16
     Parenthood
    1.16
    arte
    1.12
    mentation
    1.11
    uberty
    1.10
     FANTASY
    1.09
    dule
    1.07
    uders
    1.04
    Activations Density 0.009%

    No Known Activations