INDEX

Explanations

events related to discovery or learning about new information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

windowFixed

-0.59

ROIT

-0.58

 Conclusions

-0.57

 transitions

-0.55

født

-0.55

yntaxException

-0.54

CppMethod

-0.54

DeleteBehavior

-0.54

LastError

-0.54

CONCLUSIONS

-0.53

POSITIVE LOGITS

 news

1.16

news

0.94

 aware

0.92

News

0.89

 notizia

0.87

 noticia

0.87

Know

0.87

 notícia

0.84

 notification

0.82

 Aware

0.80

Activations Density 0.231%

events related to discovery or learning about new information

No Comments

No Known Activations