INDEX

Explanations

phrases indicating uncertainty or ambiguity

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

Uncertainty, speculation, or doubt

np_acts-logits-general · gemini-2.0-flash

s

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

RenderAtEndOf

-1.10

 autorytatywna

-1.05

ագրություններ

-1.02

 beginnetje

-0.95

 ModelRenderer

-0.87

 فريبيس

-0.81

AndEndTag

-0.81

Controllo

-0.79

 houſe

-0.77

 الرياضيه

-0.77

POSITIVE LOGITS

 unclear

0.86

 clear

0.63

 seems

0.54

clear

0.53

 remains

0.51

 questionable

0.49

 unsure

0.48

yet

0.47

 jelas

0.47

 Seems

0.46

Activations Density 0.209%

phrases indicating uncertainty or ambiguity

Uncertainty, speculation, or doubt

s

No Comments

No Known Activations