INDEX

Explanations

the term "Ind" and its variations, which likely pertain to a specific subject or concept throughout the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

tagHelperRunner

-0.78

>{@

-0.75

 مشين

-0.75

 مشارکت‌کنندگان

-0.71

 calendriers

-0.70

bagno

-0.67

 Mathew

-0.64

 municipale

-0.62

MessageOf

-0.62

 cref

-0.61

POSITIVE LOGITS

Ind

4.23

Ind

3.94

ind

3.38

IND

3.36

ind

3.14

IND

3.05

indi

2.16

 indi

2.12

 Indi

1.90

 indo

1.80

Activations Density 0.074%

the term "Ind" and its variations, which likely pertain to a specific subject or concept throughout the document

No Comments

No Known Activations