INDEX

Explanations

phrases indicating clarity and emphasis in statements or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

fjspx

-0.79

+#+

-0.65

 insensible

-0.64

 bershka

-0.61

 iſt

-0.60



-0.59

UrlResolution

-0.55

 للاسماء

-0.55

BeginInit

-0.55

ImageField

-0.53

POSITIVE LOGITS

 clear

1.98

 clearly

1.78

clear

1.63

 CLEAR

1.61

clearly

1.53

 Clear

1.50

 Clearly

1.48

 duidelijk

1.47

Clear

1.46

 clearest

1.41

Activations Density 0.471%

phrases indicating clarity and emphasis in statements or opinions

No Comments

No Known Activations