INDEX

Explanations

phrases indicating the concept of "opposites."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

StoryboardSegue

-0.86

createClass

-0.84

tvguidetime

-0.78

ViewImports

-0.78

complexContent

-0.75

DeleteBehavior

-0.72

 चीज़ों

-0.72

onViewCreated

-0.70

HttpPut

-0.68

yntaxException

-0.68

POSITIVE LOGITS

个

0.77

 entire

0.77

 whole

0.72

entire

0.71

 ganzen

0.66

whole

0.64

多个

0.62

 inteiro

0.60

個

0.60

Entire

0.58

Activations Density 0.148%

phrases indicating the concept of "opposites."

No Comments

No Known Activations