INDEX

Explanations

XML or HTML closing tags in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AsUp

-1.00

 Numerade

-0.78

fromCharCode

-0.67

Personendaten

-0.67

LookAnd

-0.66

ⓧ

-0.63

Vidite

-0.62

StoreMessageInfo

-0.61

المناصب

-0.61

 мәкал

-0.60

POSITIVE LOGITS

 summary

1.18

summary

1.12

 Summary

1.02

Summary

0.97

 SUMMARY

0.93

SUMMARY

0.88

 summaries

0.86

 summarized

0.85

 summarize

0.81

 resumen

0.76

Activations Density 0.019%

XML or HTML closing tags in the text

No Comments

No Known Activations