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

    instances of the character "ĉ" or variations in styling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    emotional responses and reactions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    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
    2:0.02
    3:0.05
    4:0.03
    5:0.06
    6:0.02
    7:0.07
    8:0.11
    9:0.02
    10:0.03
    11:0.47
    Negative Logits
    ‐
    -4.02
     ­
    -3.89
    )—
    -3.48
    —
    -3.40
    —"
    -3.24
    —-
    -3.19
     "…
    -3.13
     –
    -2.86
     geo
    -2.83
     organis
    -2.78
    POSITIVE LOGITS
    JUST
    5.60
    `.
    5.48
     ----------------------------------------------------------------
    5.14
    ..."
    4.72
     [...]
    4.71
    ........
    4.70
    ...]
    4.67
    ``
    4.62
    `
    4.59
     --------------------------------
    4.46
    Activations Density 0.003%

    No Known Activations