INDEX

Explanations

instances related to reflection and contemplation

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

"reflect" and "reflection"

np_acts-logits-general · gemini-2.0-flash

reflects or reflects on

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 configureStore

-0.75

paravant

-0.59

 Kün

-0.58

ourable

-0.58

 صوتيه

-0.57

BufferException

-0.57

ख्या

-0.56

zyna

-0.56

робнее

-0.56

 MongoClient

-0.55

POSITIVE LOGITS

 reflections

1.24

 refle

1.24

 reflect

1.18

 Reflect

1.18

 reflecting

1.18

 reflection

1.15

 reflects

1.14

reflect

1.13

 Refle

1.10

 reflected

1.08

Activations Density 0.070%

instances related to reflection and contemplation

"reflect" and "reflection"

reflects or reflects on

No Comments

No Known Activations