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. 44290
    Prev
    Next
    INDEX
    Explanations

    key phrases related to the need for further research and investigation

    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
    1:0.02
    2:0.15
    3:0.12
    4:0.10
    5:0.03
    6:0.06
    7:0.10
    8:0.05
    9:0.04
    10:0.13
    11:0.14
    Negative Logits
    kill
    -1.45
    ーティ
    -1.42
    っ
    -1.38
    ゴ
    -1.37
     サーティワン
    -1.35
     crap
    -1.32
     Screw
    -1.31
    シ
    -1.27
     Shit
    -1.25
    ナ
    -1.25
    POSITIVE LOGITS
    izons
    1.64
    doi
    1.41
     forthcoming
    1.38
    hess
    1.32
    adan
    1.32
     casinos
    1.31
     uncertainties
    1.30
     pending
    1.28
     inquire
    1.28
    rencies
    1.27
    Activations Density 0.003%

    No Known Activations