INDEX

Explanations

phrases that convey equivalence or similarity in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

matmul

-0.53

AsUp

-0.51

 <=",

-0.51

PDOException

-0.50

goire

-0.49

出版年

-0.46

 contextLoads

-0.45

Getenv

-0.45

__':

-0.45

 ellers

-0.44

POSITIVE LOGITS

 synonymous

1.31

 interchangeably

1.10

same

1.02

 synonym

1.01

 same

0.99

 dasselbe

0.98

 hetzelfde

0.96

Same

0.95

SAME

0.93

 Same

0.92

Activations Density 0.476%

phrases that convey equivalence or similarity in context

No Comments

No Known Activations