INDEX

Explanations

lines or segments that signal a structural or formatting component

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

<bos>

-0.86

errHandler

-0.73

LabelTagHelper

-0.72

 externi

-0.71

")),

-0.71

 Italijanski

-0.70

Personensuche

-0.69

"]),

-0.69

']),

-0.68

]),

-0.66

POSITIVE LOGITS

 contextLoads

0.68

 Touchable

0.64

󠁮

0.62

 BoxFit

0.59

ScreenState

0.59

تقاوى

0.59

^(@)

0.57

 CGPoint

0.57

ῳ

0.57

 ModelAndView

0.56

Activations Density 0.197%

lines or segments that signal a structural or formatting component

No Comments

No Known Activations