INDEX

Explanations

phrases related to determining or dictating conditions and factors within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 recent

-0.52

 rius

-0.47

checkNotNull

-0.46

 Greif

-0.45

(/\

-0.45

Recent

-0.44

askins

-0.44

 sekal

-0.44

 reciente

-0.43

UD

-0.43

POSITIVE LOGITS

 dictate

0.93

 define

0.93

 dictated

0.93

 defining

0.91

 Defines

0.90

 defines

0.84

 Define

0.82

 dictates

0.81

 Defining

0.80

出版年

0.79

Activations Density 0.447%

phrases related to determining or dictating conditions and factors within various contexts

No Comments

No Known Activations