INDEX

Explanations

names of organizations and initiatives related to healthcare and research

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

[Word] [Association/Program/Service]

np_acts-logits-general · gemini-2.0-flash

prevention programs and services

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 gouver

-0.47

-0.44

ultad

-0.41

hom

-0.40

car

-0.40

 רב

-0.40

kr

-0.40

 mente

-0.40

uari

-0.39

 GOVERNMENT

-0.39

POSITIVE LOGITS

 يتيمه

1.03

OGND

0.77

 nakalista

0.76

sprzedam

0.76

Diweddarwch

0.76

 <<<<<<<<<<<<<<

0.76

WithIOException

0.75

HandlerContext

0.74

SourceChecksum

0.73

ValueGenerated

0.72

Activations Density 0.410%

names of organizations and initiatives related to healthcare and research

[Word] [Association/Program/Service]

prevention programs and services

No Comments

No Known Activations