INDEX

Explanations

terms related to legal language and implications

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

"the" followed by abstract nouns

np_acts-logits-general · gemini-2.0-flash

the importance or purpose

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

Autoritní

-0.56

 estekak

-0.56

 NSCoder

-0.54

 przecież

-0.53

AutoScaleMode

-0.53

yaszt

-0.52

MigrationBuilder

-0.52

transQ

-0.52

 himo

-0.51

IVEREF

-0.51

POSITIVE LOGITS

 importance

1.28

 reasons

1.24

 significance

1.20

 meaning

1.14

 implications

1.13

why

1.11

 origins

1.07

 rationale

1.06

 ways

1.00

 raisons

1.00

Activations Density 0.514%

terms related to legal language and implications

"the" followed by abstract nouns

the importance or purpose

No Comments

No Known Activations