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

    Neuronpedia

    APICircuit 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. 44405
    Prev
    Next
    INDEX
    Explanations

    references to state-of-the-art technology or practices in various contexts

    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
    0:0.02
    1:0.01
    2:0.15
    3:0.05
    4:0.05
    5:0.02
    6:0.06
    7:0.27
    8:0.04
    9:0.03
    10:0.10
    11:0.14
    Negative Logits
     veto
    -1.67
    ername
    -1.63
    fax
    -1.63
    enary
    -1.57
    obyl
    -1.45
    ratulations
    -1.39
    ividual
    -1.38
    icus
    -1.37
     Nerd
    -1.36
     elbows
    -1.33
    POSITIVE LOGITS
     Ukrain
    1.51
    ahime
    1.34
     domestically
    1.33
    Definition
    1.33
    Sov
    1.31
     Cruise
    1.26
     LOC
    1.22
     adjustment
    1.22
    enezuel
    1.21
     Afgh
    1.21
    Activations Density 0.000%

    No Known Activations