INDEX

Explanations

symbols and formatting elements in the 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

หวัด

-0.59

droje

-0.59

=$?

-0.55

NSNumber

-0.53

MessageOf

-0.53

TagMode

-0.52

AsUp

-0.52

Demografie

-0.52

 تضيفلها

-0.51

NSArray

-0.51

POSITIVE LOGITS

0.94

·

0.77

∙

0.73

│

0.73

:✨

0.72

•

0.69

ValueStyle

0.69

|=

0.69

0.67

)|\

0.66

Activations Density 0.153%

symbols and formatting elements in the text

No Comments

No Known Activations