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. 7758
    Prev
    Next
    INDEX
    Explanations

    terminology related to networking protocols and technologies

    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
    0:0.02
    1:0.05
    2:0.13
    3:0.15
    4:0.02
    5:0.03
    6:0.16
    7:0.10
    8:0.04
    9:0.06
    10:0.05
    11:0.15
    Negative Logits
    advertising
    -1.42
    ERY
    -1.22
    hyde
    -1.14
     dere
    -1.12
    PLIC
    -1.08
     omission
    -1.08
    ahime
    -1.07
    �
    -1.07
    mma
    -1.04
     linger
    -1.03
    POSITIVE LOGITS
    anguage
    1.43
    rencies
    1.35
    uctor
    1.30
    imensional
    1.24
    dot
    1.19
    ombat
    1.18
    Enabled
    1.16
     solves
    1.09
     Detect
    1.08
    pload
    1.07
    Activations Density 0.004%

    No Known Activations