INDEX

Explanations

terms related to specificity and uniqueness in scientific contexts

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

specific adjectives followed by prepositions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

-0.62

hasMoreElements

-0.54

wsdl

-0.52

 bocca

-0.52

 защото

-0.50

principalTable

-0.49

 stället

-0.48

 noget

-0.48

󠁢

-0.46

POSITIVE LOGITS

Gambas

0.71

enseits

0.66

adaptiveStyles

0.65

 AttributeSet

0.60

Skocz

0.60

 ब्रेकडाउन

0.59

เภ

0.58

utched

0.58

ๆ

0.57

izielle

0.57

Activations Density 0.406%

terms related to specificity and uniqueness in scientific contexts

specific adjectives followed by prepositions

No Comments

No Known Activations