INDEX

Explanations

phrases related to planning and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 tartalomajánló

-0.86

 EClass

-0.79

Personensuche

-0.78

 newBuilder

-0.77

 however

-0.74

 للمعارف

-0.73

 noqa

-0.72

AndEndTag

-0.71

 useAppContext

-0.71

however

-0.70

POSITIVE LOGITS

 sitten

0.74

又被

0.67

 afterwards

0.61

 thereafter

0.61

又有

0.60

 потом

0.58

又

0.57

 again

0.56

 afterward

0.55

Then

0.55

Activations Density 0.773%

phrases related to planning and decision-making processes

No Comments

No Known Activations