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. 7836
    Prev
    Next
    INDEX
    Explanations

    references to downloadable content (DLC) for video games

    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
    0:0.03
    1:0.04
    2:0.05
    3:0.07
    4:0.03
    5:0.07
    6:0.11
    7:0.27
    8:0.06
    9:0.04
    10:0.08
    11:0.08
    Negative Logits
    ahu
    -1.38
    iazep
    -1.23
    omet
    -1.17
    vard
    -1.16
    yd
    -1.16
    mie
    -1.10
    fer
    -1.09
    uty
    -1.06
     Quincy
    -1.03
    ocent
    -1.03
    POSITIVE LOGITS
     showcased
    1.37
     revamped
    1.23
    Characters
    1.22
     standalone
    1.22
     expansions
    1.20
    senal
    1.20
     Destination
    1.19
     entirety
    1.19
    ��
    1.19
     Enhance
    1.18
    Activations Density 0.021%

    No Known Activations