© 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. 35839
    Prev
    Next
    INDEX
    Explanations

    negative connotations or contexts related to environmental conditions

    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
    0:0.08
    1:0.05
    2:0.08
    3:0.09
    4:0.11
    5:0.08
    6:0.09
    7:0.07
    8:0.08
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
     Werewolf
    -1.69
    sic
    -1.62
    chwitz
    -1.62
    cients
    -1.58
    ete
    -1.56
     Saiyan
    -1.52
    aternity
    -1.49
     Flavoring
    -1.48
     Warlock
    -1.46
    ovi
    -1.44
    POSITIVE LOGITS
    channelAvailability
    1.75
     palm
    1.48
     autop
    1.45
    dayName
    1.45
     fingert
    1.44
    �
    1.41
     relent
    1.40
     pods
    1.31
     Ampl
    1.30
     illustrate
    1.29
    Activations Density 0.000%

    No Known Activations