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. 5-ATT-KK
    6. 2779
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

    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
    0:0.03
    1:0.02
    2:0.09
    3:0.11
    4:0.07
    5:0.04
    6:0.04
    7:0.14
    8:0.06
    9:0.05
    10:0.17
    11:0.13
    Negative Logits
     predomin
    -1.49
     multipl
    -1.37
     ethnicity
    -1.35
    orney
    -1.35
     Parenthood
    -1.31
     gangs
    -1.29
     struggles
    -1.26
    ulative
    -1.24
     differentiate
    -1.24
     socio
    -1.23
    POSITIVE LOGITS
    hemer
    1.42
    Title
    1.38
    original
    1.37
     srfN
    1.37
    ollow
    1.35
    BTC
    1.33
    ribly
    1.33
    Untitled
    1.32
    animous
    1.31
    archive
    1.30
    Activations Density 0.000%

    No Known Activations