INDEX

Explanations

references to the need for functionalities or improvements in a system or process

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

Immediately precedes "would"

np_acts-logits-general · gemini-2.0-flash

would

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

 autorytatywna

-0.83

İstinadlar

-0.77

ésultat

-0.76

úgó

-0.73

 >=",

-0.73

ModelSerializer

-0.70

__":

-0.70

parsedMessage

-0.69

 itſelf

-0.69

webElementXpaths

-0.69

POSITIVE LOGITS

 would

3.62

would

3.12

 Would

2.96

Would

2.84

 WOULD

2.62

 wouldn

2.25

wouldn

1.95

 Wouldn

1.87

Wouldn

1.83

 wouldnt

1.81

Activations Density 1.735%

references to the need for functionalities or improvements in a system or process

Immediately precedes "would"

would

No Comments

No Known Activations