INDEX

Explanations

phrases indicating opinions, societal interactions, and the complexities of relationships

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

preceding a negation

np_acts-logits-general · gemini-2.0-flash

conjunctions and negations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

FirstResponder

-0.42

vu

-0.42

лтамалар

-0.40

 saat

-0.38

arc

-0.35

发表于

-0.35

tagext

-0.35

meg

-0.35

 Beach

-0.35

moon

-0.34

POSITIVE LOGITS

 zijne

0.63

 myſelf

0.62

 plufieurs

0.59

 pouvoit

0.57

genodigd

0.56

 Infór

0.55

majánló

0.54

IntOverflow

0.52

aarrggbb

0.50

 feroit

0.49

Activations Density 2.162%

phrases indicating opinions, societal interactions, and the complexities of relationships

preceding a negation

conjunctions and negations

No Comments

No Known Activations