INDEX

Explanations

references to design elements in a digital context

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

Tokens after max activating period or colon

np_acts-logits-general · gemini-2.0-flash

image urls and references

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

toHaveBeenCalled

-0.61

EditorBrowsable

-0.55

جستارهای

-0.50

Související

-0.47

Vezi

-0.47

makeText

-0.47

fromnode

-0.47

ارتمان

-0.43

aarrggbb

-0.42

zaamheid

-0.42

POSITIVE LOGITS

 image

1.93

 picture

1.75

 images

1.74

 Image

1.61

image

1.61

 photo

1.57

 pictures

1.56

Image

1.51

 photograph

1.50

 IMAGE

1.49

Activations Density 0.284%

references to design elements in a digital context

Tokens after max activating period or colon

image urls and references

No Comments

No Known Activations