INDEX

Explanations

symbols and formatting in data or code

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

Text after special characters or symbols

np_acts-logits-general · gemini-2.0-flash

content/document structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ItemBackground

-0.73

########.

-0.70

 <<<<<<<<<<<<<<

-0.67

Vidite

-0.63

ⓧ

-0.61

IntoConstraints

-0.60

★★★★☆

-0.59

TypedDataSet

-0.59

 Biôgrafia

-0.58

SharedDtor

-0.57

POSITIVE LOGITS

section

0.98

<b>

0.68

 section

0.65

 sections

0.58

<strong>

0.56

sections

0.52

ção

0.50

 SECTION

0.50

UnusedPrivate

0.48

 Saltar

0.48

Activations Density 0.032%

symbols and formatting in data or code

Text after special characters or symbols

content/document structure

No Comments

No Known Activations