INDEX

Explanations

negative phrases or expressions of refusal

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

Contractions with "not": don't, isn't, etc

np_acts-logits-general · gemini-2.0-flash

don't worry, don't forget, don't expect

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

 ferons

-0.63

UniformLocation

-0.60

ficamente

-0.51

روابط

-0.51

Aiheesta

-0.49

 חיצוניים

-0.49

Ծանոթ

-0.48

 verrez

-0.45

 cabang

-0.45

Linki

-0.45

POSITIVE LOGITS

 forget

1.19

 Forget

0.81

 misunderstand

0.77

forget

0.77

 worry

0.76

Forget

0.74

 FORGET

0.73

 ModelExpression

0.73

 underestimate

0.69

 forgetting

0.66

Activations Density 0.055%

negative phrases or expressions of refusal

Contractions with "not": don't, isn't, etc

don't worry, don't forget, don't expect

No Comments

No Known Activations