Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 8464
    Prev
    Next
    INDEX
    Explanations

    sentences that convey emotional responses and personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.15
    2:0.07
    3:0.02
    4:0.15
    5:0.10
    6:0.05
    7:0.03
    8:0.06
    9:0.13
    10:0.06
    11:0.04
    Negative Logits
     fucking
    -1.76
     goddamn
    -1.69
    �
    -1.68
     fuckin
    -1.64
     cunt
    -1.57
     fuck
    -1.57
     whore
    -1.53
    !".
    -1.51
     shit
    -1.51
    assic
    -1.49
    POSITIVE LOGITS
     Earlier
    1.81
    iannopoulos
    1.64
     According
    1.49
    oulos
    1.45
     Asked
    1.44
     Pacers
    1.44
    ierrez
    1.41
     DeVos
    1.39
    quartered
    1.39
    bourg
    1.38
    Activations Density 0.106%

    No Known Activations