INDEX

Explanations

terms related to cells and immune responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

at

-0.51

 pomoc

-0.47

 belang

-0.47

 slits

-0.46

 žem

-0.46

פת

-0.44

DoubleQuotes

-0.44

 caes

-0.44

velo

-0.43

POSITIVE LOGITS

etc

0.95

 Мексичка

0.87

and

0.79

!("{

0.73

Etc

0.72

etc

0.71

 समीक्षक

0.70

theoremstyle

0.69

 그리고

0.67

 TimeUnit

0.65

Activations Density 0.295%

terms related to cells and immune responses

No Comments

No Known Activations