INDEX

Explanations

patterns related to structured data or coding syntax

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

The number "1"

np_acts-logits-general · gemini-2.0-flash

the number 1

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

twimg

-0.58

 együtt

-0.51

 مواليد

-0.51

 vectorielles

-0.49

%)$

-0.48

ראלי

-0.47

pH

-0.47

 tegas

-0.47

brainly

-0.47

uolo

-0.47

POSITIVE LOGITS

 HasFactory

0.62

 Homicide

0.58

 legged

0.58

 للاسماء

0.56

 arbore

0.55

########.

0.55

 Artis

0.54

InSection

0.53

 fieldNum

0.53

 papilla

0.52

Activations Density 1.097%

patterns related to structured data or coding syntax

The number "1"

the number 1

No Comments

No Known Activations