INDEX

Explanations

keywords related to scientific classifications and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 متعلقه

-0.78

RenderAtEndOf

-0.74

Clik

-0.74

 arşivlendi

-0.72

WriteBarrier

-0.71

contentLoaded

-0.70

 doInBackground

-0.70

oredCriteria

-0.68

WithIOException

-0.68

 سكانية

-0.66

POSITIVE LOGITS

ברת

0.61

 phrase

0.55

 geslacht

0.55

USS

0.55

 planet

0.52

 labdar

0.51

 hermanas

0.51

เช่น

0.50

 namens

0.50

 слово

0.50

Activations Density 0.647%

keywords related to scientific classifications and terms

No Comments

No Known Activations