INDEX

Explanations

phrases related to problem-solving or troubleshooting

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

 –,

-0.74

astră

-0.67

 résumé

-0.65

 Erdoğan

-0.65

 Māori

-0.64

 MÉXICO

-0.64

iläum

-0.63

تماد

-0.63

 entrées

-0.63

mità

-0.63

POSITIVE LOGITS

 wasnt

0.99

 doesnt

0.98

 didnt

0.98

 isnt

0.97

 Thats

0.96

 thats

0.91

 arent

0.91

 youll

0.89

 theyre

0.89

Dont

0.87

Activations Density 0.187%

phrases related to problem-solving or troubleshooting

No Comments

No Known Activations