© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28403
    Prev
    Next
    INDEX
    Explanations

    code-related syntax or errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.07
    1:0.44
    2:0.03
    3:0.03
    4:0.03
    5:0.13
    6:0.04
    7:0.02
    8:0.03
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
    Downloadha
    -2.41
     acknowled
    -1.90
    ゴン
    -1.83
    prints
    -1.78
    Pages
    -1.77
    Paper
    -1.72
     Emails
    -1.71
     Puzzles
    -1.70
     Phone
    -1.70
    Acknowled
    -1.69
    POSITIVE LOGITS
     bloc
    2.28
    choice
    2.22
     group
    2.15
     coalition
    2.14
     GROUP
    2.13
    amily
    2.12
    group
    2.11
    roup
    2.09
    Group
    2.06
     GOODMAN
    1.99
    Activations Density 0.072%

    No Known Activations