INDEX

Explanations

occurrences of the term "series."

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

"series"

np_acts-logits-general · gemini-2.0-flash

series of

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-0.79

сылкі

-0.76

🏻

-0.70

 Monfieur

-0.66

AnchorTagHelper

-0.66

 ſeveral

-0.65

Eſ

-0.64

 Inſ

-0.63

Спасылкі

-0.63

 raiſ

-0.63

POSITIVE LOGITS

 Series

0.88

 SERIES

0.80

 series

0.80

Series

0.78

 Série

0.77

Série

0.68

entas

0.67

jooq

0.64

={({

0.64

eniu

0.63

Activations Density 0.066%

occurrences of the term "series."

"series"

series of

No Comments

No Known Activations