INDEX

Explanations

phrases that denote descriptions or classifications of entities

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

alternate names or abbreviations

np_acts-logits-general · gemini-2.0-flash

called or known as

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelperRunner

-0.80

GEBURTSDATUM

-0.77

ंदीखरीदारी

-0.74

 kaarangay

-0.63

parsedMessage

-0.62

észetes

-0.62

eleste

-0.62

RenderAtEndOf

-0.62

hoeddwyd

-0.61

eseorang

-0.61

POSITIVE LOGITS

 name

0.95

 called

0.87

 names

0.84

 named

0.84

 affectionately

0.81

称为

0.80

name

0.79

Called

0.79

叫做

0.76

 nickname

0.76

Activations Density 0.276%

phrases that denote descriptions or classifications of entities

alternate names or abbreviations

called or known as

No Comments

No Known Activations