INDEX

Explanations

terms related to proximity and quantity

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

Follows bullet points (•)

np_acts-logits-general · gemini-2.0-flash

nearly everywhere

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

QMetaType

-0.83

NSM

-0.83

OfBirth

-0.81

 shuff

-0.81

zwe

-0.80

MOV

-0.80

 Camin

-0.79

dillos

-0.78

Arqu

-0.77

 tartalomajánló

-0.77

POSITIVE LOGITS

er

1.62

ER

1.12

••

0.92

 Brenner

0.91

ν

0.88

 Phipps

0.88

.•

0.87

••••

0.81

•

0.81

 Xperia

0.79

Activations Density 0.168%

terms related to proximity and quantity

Follows bullet points (•)

nearly everywhere

No Comments

No Known Activations