INDEX

Explanations

expressions of fascination or interest in topics

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

Expressing intrigue or curiosity

np_acts-logits-general · gemini-2.0-flash

something is interesting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

ConstraintMaker

-0.74

Ӕ

-0.72

IntoConstraints

-0.66

:✨

-0.65

RTLR

-0.63

SBATCH

-0.63

ViewImports

-0.63

AsUp

-0.61

 للاسماء

-0.59

 noDo

-0.58

POSITIVE LOGITS

 interesting

1.16

interesting

1.04

 Interesting

1.00

Interesting

1.00

 intriguing

0.96

 fascinating

0.92

 interesante

0.91

 interessante

0.84

 cieka

0.80

 interestingly

0.75

Activations Density 0.204%

expressions of fascination or interest in topics

Expressing intrigue or curiosity

something is interesting

No Comments

No Known Activations