INDEX

Explanations

symbols and formatting elements in text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ontale

-0.49

ETIES

-0.49

 références

-0.49

 ViewGroup

-0.48

root

-0.47

älte

-0.47

 geladeira

-0.46

imedia

-0.45

 делу

-0.44

goku

-0.44

POSITIVE LOGITS

+#+#

0.83

tagHelperRunner

0.73

principalTable

0.67

ArrowToggle

0.66

 htons

0.66

sidemargin

0.65

 ComVisible

0.64

 pinulongan

0.64

GEBURTSDATUM

0.63

IonicModule

0.62

Activations Density 0.494%

symbols and formatting elements in text

No Comments

No Known Activations