INDEX

Explanations

questions and expressions of uncertainty or inquiry

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

" at the end of sentence or clause

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

Negative Logits

â

-0.71

“

-0.70

‘

-0.68

„

-0.67

–

-0.67

-0.65

 ‘‘

-0.64

Архівовано

-0.63

“

-0.62

”

-0.61

POSITIVE LOGITS

 XNUMX

0.95

 Réponses

0.91

 houſe

0.90

 pleaſure

0.87

awtextra

0.86

 abſ

0.86

 ſtate

0.86

 ainfi

0.84

 purpoſe

0.83

 greateſt

0.82

Activations Density 0.198%

questions and expressions of uncertainty or inquiry

" at the end of sentence or clause

No Known Activations