INDEX

Explanations

questions and statements about information sharing and decision-making

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

也很

-0.72

also

-0.69

 also

-0.68

也非常

-0.66

 también

-0.60

very

-0.60

Очень

-0.60

ook

-0.59

 очень

-0.58

almost

-0.57

POSITIVE LOGITS

 réellement

0.75

 surla

0.74

 poszczegól

0.74

บ้าง

0.71

 ACTUALLY

0.71

 realistically

0.71

 fakty

0.70

 realmente

0.70

 best

0.69

 ulike

0.69

Activations Density 0.360%

questions and statements about information sharing and decision-making

No Comments

No Known Activations