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. 19
    Prev
    Next
    INDEX
    Explanations

    specific dates and numerical statistics

    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
    1:0.47
    2:0.03
    3:0.03
    4:0.03
    5:0.06
    6:0.08
    7:0.03
    8:0.02
    9:0.09
    10:0.03
    11:0.04
    Negative Logits
    ived
    -2.73
    ivas
    -2.42
    claim
    -2.41
    intendent
    -2.41
    ivo
    -2.38
    ァ
    -2.32
    iv
    -2.32
    iva
    -2.31
    ills
    -2.29
    iving
    -2.28
    POSITIVE LOGITS
    laughter
    2.78
    PLIC
    2.78
    blers
    2.67
    ._
    2.65
    222
    2.59
    uble
    2.58
    223
    2.52
    otal
    2.51
    003
    2.48
    083
    2.46
    Activations Density 0.022%

    No Known Activations