© 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. 9-ATT-KK
    6. 2923
    Prev
    Next
    INDEX
    Explanations

    occurrences of high-impact statistical or numerical data

    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
    1:0.45
    2:0.07
    3:0.07
    4:0.05
    5:0.05
    6:0.04
    7:0.05
    8:0.02
    9:0.04
    10:0.05
    11:0.02
    Negative Logits
    ulously
    -2.64
    aq
    -2.25
    76561
    -2.21
    xxxx
    -2.18
    estern
    -2.18
    xxx
    -2.08
     consisted
    -2.05
    urned
    -2.03
    spect
    -2.02
    iann
    -1.98
    POSITIVE LOGITS
     more
    6.12
     fewer
    5.86
    more
    5.67
     greater
    5.46
     harder
    5.27
     MORE
    5.21
     less
    5.16
    More
    5.12
     clearer
    5.05
     wiser
    4.83
    Activations Density 0.244%

    No Known Activations