INDEX

Explanations

references to data types and database concepts

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

Followed by the word "one"

np_acts-logits-general · gemini-2.0-flash

counting 'one'

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

tinyos

-0.61

الحياه

-0.56

 CreateTagHelper

-0.56

 Мексичка

-0.54

thoven

-0.51

 فريبيس

-0.47

 للمعارف

-0.47

ayon

-0.47

+#+

-0.47

ərbaycan

-0.47

POSITIVE LOGITS

one

3.44

one

2.25

 één

2.14

 یکی

2.01

 unul

1.97

 один

1.93

 jednego

1.93

 jednej

1.91

 одного

1.90

 אחד

1.88

Activations Density 1.138%

references to data types and database concepts

Followed by the word "one"

counting 'one'

No Comments

No Known Activations