INDEX

Explanations

quantifiers and discussions of scale or size

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

 Meksiku

-0.61

ThroughAttribute

-0.57

 Hän

-0.54

 mergeFrom

-0.54

 contextLoads

-0.53

Tembelea

-0.52

ともに

-0.51

NameInMap

-0.51

posób

-0.50

SharedCtor

-0.50

POSITIVE LOGITS

 CreateTagHelper

1.01

 reason

1.01

 possibility

0.98

 tendency

0.93

 difference

0.91

 chance

0.84

possibility

0.84

 need

0.83

 dearth

0.80

 shortage

0.80

Activations Density 0.210%

quantifiers and discussions of scale or size

No Comments

No Known Activations