INDEX

Explanations

structured data, particularly statistics or figures related to research or organizational types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 termes

-0.52

VisualStudio

-0.47

 Wallflower

-0.44

 Placebo

-0.44

rees

-0.43

triques

-0.43

ән

-0.42

 terme

-0.42

audi

-0.42

 nocturn

-0.42

POSITIVE LOGITS

 Chwiliwch

0.78

istoitu

0.71

 NUKAT

0.61

 <=",

0.59

 MotionEvent

0.58

각주

0.57

CITATION

0.56

 IndexPath

0.56

 odkazy

0.55

 kaynağından

0.55

Activations Density 0.335%

structured data, particularly statistics or figures related to research or organizational types

No Comments

No Known Activations