INDEX

Explanations

references to the concept of returning or going back in various contexts

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

"back"

np_acts-logits-general · gemini-2.0-flash

back then or back when

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

URLException

-0.94

뀜

-0.90

 Winaray

-0.90

뀐

-0.82

 Roskov

-0.82

 ویکی‌پدیای

-0.81

HideFlags

-0.80

Cuánt

-0.80

••••

-0.79

✨:

-0.79

POSITIVE LOGITS

Back

1.25

back

1.25

 Back

1.20

 back

1.19

 BACK

1.17

BACK

1.17

 backs

1.02

 indietro

0.93

backs

0.92

btnBack

0.87

Activations Density 0.105%

references to the concept of returning or going back in various contexts

"back"

back then or back when

No Comments

No Known Activations