INDEX

Explanations

references to consequences and impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

On

-1.55

On

-1.55

ON

-1.50

ON

-1.49

 onto

-1.29

onto

-1.25

 UPON

-1.21

Ont

-1.19

upon

-1.16

 SOBRE

-1.14

POSITIVE LOGITS

RegistryLite

0.59

 Offisielt

0.59

tagHelperRunner

0.58

日閲覧

0.56

 '\\;'

0.53

出版年

0.52

chik

0.51

 Paglinawan

0.51

Rhestr

0.50

WaitGroup

0.50

Activations Density 0.412%

references to consequences and impacts

No Comments

No Known Activations