© 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. 28347
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and personal experiences of distress or transformation

    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
    1:0.04
    2:0.07
    3:0.23
    4:0.07
    5:0.06
    6:0.03
    7:0.03
    8:0.08
    9:0.08
    10:0.16
    11:0.07
    Negative Logits
     embattled
    -1.79
     advocates
    -1.52
     ):
    -1.46
    quartered
    -1.46
     Accessed
    -1.44
     Canaver
    -1.44
     proponents
    -1.44
     ®
    -1.40
    ielding
    -1.38
     embodiments
    -1.38
    POSITIVE LOGITS
    ..."
    2.42
     …"
    2.39
    ..."
    2.38
    .""
    2.29
     ['
    2.27
    …"
    2.22
    )."
    2.15
    …."
    2.13
     [
    2.12
     [...]
    2.02
    Activations Density 0.643%

    No Known Activations