INDEX

Explanations

phrases indicating possibility or uncertainty

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

possible that

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 oprot

-0.66

 <<<<<<<<<<<<<<

-0.63

 Italijani

-0.60

+#+

-0.59

 protoimpl

-0.58

 pewno

-0.57

 provavelmente

-0.55

WebElementEntity

-0.54

Autoritní

-0.54

 typically

-0.52

POSITIVE LOGITS

 some

0.50

 algunos

0.44

 bazı

0.41

 they

0.41

some

0.40

 algunas

0.40

 некоторые

0.38

 للمعارف

0.38

 alguno

0.38

Some

0.37

Activations Density 0.032%

phrases indicating possibility or uncertainty

possible that

No Comments

No Known Activations