INDEX

Explanations

phrases that indicate completion or conclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

SIS

-0.70

 Fauci

-0.70

createCanvas

-0.68

 vigilance

-0.67

@[

-0.67

 courseId

-0.66

 Leuven

-0.66

 sessile

-0.66

Приготовление

-0.66

 noct

-0.66

POSITIVE LOGITS

 desem

0.70

 being

0.68

 побы

0.67

ization

0.65

 jadi

0.64

CppMethod

0.63

munk

0.62

 lượt

0.62

tvguidetime

0.62

be

0.62

Activations Density 0.078%

phrases that indicate completion or conclusion

No Comments

No Known Activations