INDEX

Explanations

instances of specific terms or phrases related to signaling pathways and biological processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 useRouter

-0.86

 Paglinawan

-0.86

CodedInputStream

-0.81

BeginContext

-0.81

principalColumn

-0.80

 acaso

-0.78

 hini

-0.78

 postIndex

-0.78

 kasarigan

-0.77

swire

-0.73

POSITIVE LOGITS

 emotions

1.49

 emotion

1.38

 Emotions

1.37

 Emotion

1.33

Emotions

1.24

emotions

1.15

emotion

1.15

 emotional

1.13

Emotion

1.12

Emo

1.09

Activations Density 0.101%

instances of specific terms or phrases related to signaling pathways and biological processes

No Comments

No Known Activations