INDEX

Explanations

variations of the word "common."

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

Following "common"

np_acts-logits-general · gemini-2.0-flash

common followed by specific terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tartalomajánló

-0.92

 StatefulWidget

-0.75

 ComVisible

-0.73

 utafitiHapana

-0.73

tagHelperRunner

-0.73

.*")]

-0.70

VersionUID

-0.68

RunWith

-0.68

MigrationBuilder

-0.68

 BoxDecoration

-0.67

POSITIVE LOGITS

ality

0.94

 Common

0.89

alities

0.89

 denominator

0.89

COMMON

0.88

 sense

0.86

Common

0.85

 COMMON

0.79

 common

0.77

alty

0.76

Activations Density 0.151%

variations of the word "common."

Following "common"

common followed by specific terms

No Comments

No Known Activations