INDEX

Explanations

expressions of gratitude

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

"Thank you" followed by a polite continuation

np_acts-logits-general · gemini-2.0-flash

saying thank you

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 חיצוניים

-0.64

URLEncoder

-0.61

 Италијани

-0.60

Siamo

-0.57

 nakalista

-0.56

mişti

-0.55

 useStyles

-0.55

 kaynağından

-0.53

도록

-0.53

 InputDecoration

-0.52

POSITIVE LOGITS

ReusableCell

0.78

 goodness

0.69

god

0.64

NOPQRST

0.60

!*\

0.60

 heavens

0.58

 Goodness

0.55

 tank

0.54

god

0.53

staking

0.52

Activations Density 0.043%

expressions of gratitude

"Thank you" followed by a polite continuation

saying thank you

No Comments

No Known Activations