INDEX

Explanations

references to trends and patterns in various contexts

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

"trend" or "trends"

np_acts-logits-general · gemini-2.0-flash

discussion of trends

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

 Kearns

-0.35

heça

-0.35

keits

-0.34

ocuk

-0.34

 fotográfica

-0.33

Kav

-0.33

asko

-0.33

 части

-0.33

Particular

-0.33

atelyn

-0.32

POSITIVE LOGITS

 trend

2.22

 trends

2.19

trend

1.99

 Trend

1.96

Trend

1.94

 Trends

1.91

trends

1.91

Trends

1.83

 TRENDS

1.72

 tendencias

1.52

Activations Density 0.218%

references to trends and patterns in various contexts

"trend" or "trends"

discussion of trends

No Comments

No Known Activations