INDEX

Explanations

specific formatting or structural elements in text, particularly the presence of tags or special characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 greateſt

-0.82

 purpoſe

-0.70

 cauſe

-0.65

 houſe

-0.65

 Diſ

-0.64

 reaſon

-0.64

 Большая

-0.62

 diſt

-0.61

 inſ

-0.61

 Houſe

-0.61

POSITIVE LOGITS

\&

0.84

et

0.84

 referenties

0.76

Jr

0.68

0.62

 <=",

0.62

 coworkers

0.62

httphttps

0.62

 متعلقه

0.61

 الرياضيه

0.60

Activations Density 0.207%

specific formatting or structural elements in text, particularly the presence of tags or special characters

No Comments

No Known Activations