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. 5-ATT-KK
    6. 44192
    Prev
    Next
    INDEX
    Explanations

    references to budgetary topics and oversight organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.05
    3:0.04
    4:0.04
    5:0.04
    6:0.43
    7:0.04
    8:0.03
    9:0.06
    10:0.06
    11:0.13
    Negative Logits
    otos
    -1.46
    aiman
    -1.40
    orable
    -1.35
    idious
    -1.30
    alos
    -1.29
    amiya
    -1.24
    ndra
    -1.22
    aterasu
    -1.21
    isner
    -1.20
    stadt
    -1.20
    POSITIVE LOGITS
    dq
    1.36
    rities
    1.34
    agent
    1.32
     Gazette
    1.31
    enment
    1.29
     Sales
    1.27
    issance
    1.27
    �
    1.26
    inces
    1.26
     Allow
    1.25
    Activations Density 0.008%

    No Known Activations