INDEX

Explanations

instances of examples or comparisons within the text

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

introducing examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

istoitu

-0.47

guiente

-0.44

owią

-0.44

AnchorStyles

-0.43

 Superan

-0.42

 kobieta

-0.42

 Infór

-0.41

enseignements

-0.41

ähteet

-0.40

 Económica

-0.40

POSITIVE LOGITS

 např

0.49

 שוליים

0.48

 particularly

0.47

例えば

0.47

たとえば

0.47

 exemplified

0.47

 textStatus

0.47

bkz

0.46

QMetaType

0.46

 exemplos

0.46

Activations Density 0.066%

instances of examples or comparisons within the text

introducing examples

No Comments

No Known Activations