INDEX

Explanations

references to processes involving splitting, managing, or executing tasks in steps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

complexType

-0.63

 correctes

-0.59

ghold

-0.57

/>";

-0.54

 wireType

-0.53

WAUKEE

-0.53

 وتسجيلات

-0.52

ContextHolder

-0.51

rawDesc

-0.51

 الحره

-0.51

POSITIVE LOGITS

 протяжении

0.73

 throughout

0.64

throughout

0.59

 Throughout

0.58

 PROGRESS

0.57

 incremental

0.57

Throughout

0.56

 Progress

0.55

 gradual

0.55

 successive

0.55

Activations Density 0.503%

references to processes involving splitting, managing, or executing tasks in steps

No Comments

No Known Activations