INDEX

Explanations

terms and phrases related to initialization processes or initiatives

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sampson

-0.62

bukkit

-0.62

########.

-0.60

dess

-0.59

克斯

-0.59

sa

-0.59

 Meeres

-0.58

fe

-0.58

noinspection

-0.58

SocketAddress

-0.57

POSITIVE LOGITS

Initi

1.79

 INITI

1.78

 Initi

1.71

 initi

1.63

initi

1.60

Initiative

1.55

 initiates

1.55

 Inici

1.54

 initiative

1.53

 initiated

1.53

Activations Density 0.045%

terms and phrases related to initialization processes or initiatives

No Comments

No Known Activations