Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 44276
    Prev
    Next
    INDEX
    Explanations

    topics related to government and politics

    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
    0:0.03
    1:0.01
    2:0.11
    3:0.13
    4:0.06
    5:0.03
    6:0.25
    7:0.03
    8:0.07
    9:0.06
    10:0.11
    11:0.07
    Negative Logits
    ️
    -1.49
    TING
    -1.38
    GH
    -1.27
    OIL
    -1.25
     screwed
    -1.22
    ּ
    -1.18
    lyak
    -1.18
    INAL
    -1.17
     downwards
    -1.16
     hashing
    -1.15
    POSITIVE LOGITS
    "}],"
    2.27
    "},{"
    1.79
    �醒
    1.50
    �士
    1.49
    common
    1.48
    rib
    1.48
    music
    1.47
    bender
    1.43
    spirit
    1.42
    render
    1.42
    Activations Density 0.003%

    No Known Activations