INDEX

Explanations

conditional statements and hypothetical situations

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

"would"

np_acts-logits-general · gemini-2.0-flash

would be, seem, appear

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Maguire

-0.71

يكب

-0.67

enumii

-0.66

yeri

-0.65

 blancas

-0.64

Tembelea

-0.64

ReusableCell

-0.64

Jîn

-0.63

 blanches

-0.61

richTextPanel

-0.61

POSITIVE LOGITS

Would

0.93

 WOULD

0.88

 Would

0.86

would

0.82

ULD

0.81

 would

0.80

 Wouldn

0.68

 sería

0.66

 habría

0.65

 gdyby

0.64

Activations Density 0.189%

conditional statements and hypothetical situations

"would"

would be, seem, appear

No Comments

No Known Activations