INDEX

Explanations

questions and inquiries about processes or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 quedarse

-0.55

bari

-0.53

cu

-0.52

Unsigned

-0.52

 крае

-0.51

fad

-0.51

жен

-0.50

 fournir

-0.50

zupeł

-0.49

 Mühl

-0.49

POSITIVE LOGITS

how

1.36

 कैसे

1.15

יצד

1.08

 ways

1.07

 cómo

1.07

HOW

1.06

 الرياضيه

1.03

How

1.01

Kako

1.01

 Nasıl

1.00

Activations Density 0.194%

questions and inquiries about processes or states

No Comments

No Known Activations