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. 5-ATT-KK
    6. 44418
    Prev
    Next
    INDEX
    Explanations

    phrases related to perception and perception's impact on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.01
    2:0.04
    3:0.05
    4:0.14
    5:0.02
    6:0.06
    7:0.36
    8:0.03
    9:0.03
    10:0.07
    11:0.09
    Negative Logits
    Snap
    -1.44
    animous
    -1.38
    Fuck
    -1.36
    Corn
    -1.34
    Crypt
    -1.32
    NAS
    -1.31
    ドラ
    -1.31
    legged
    -1.30
    Bang
    -1.29
    JECT
    -1.29
    POSITIVE LOGITS
     materially
    1.69
     promotions
    1.61
     efforts
    1.58
    effic
    1.56
     detract
    1.55
     substantially
    1.53
     morale
    1.51
     greatly
    1.51
     considerably
    1.48
     undue
    1.47
    Activations Density 0.001%

    No Known Activations