INDEX

Explanations

phrases and expressions related to uncertainty or vague descriptions

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

something like that

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

Autoritní

-0.85

tamment

-0.76

Билгалдахарш

-0.75

 Baillargeon

-0.74

 BoxDecoration

-0.71

Lähteet

-0.70

Viited

-0.69

 Majefty

-0.68

Portail

-0.67

 ſeveral

-0.67

POSITIVE LOGITS

 similar

0.80

 alike

0.71

 like

0.68

 whatnot

0.67

 similares

0.65

like

0.65

similar

0.63

 semacam

0.62

etc

0.61

etc

0.61

Activations Density 0.024%

phrases and expressions related to uncertainty or vague descriptions

something like that

No Comments

No Known Activations