INDEX

Explanations

mentions of scientific or technical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 дописавши

-0.65

]='\

-0.61

RenderAtEndOf

-0.57

 hereof

-0.55

Примечания

-0.53

 BoxDecoration

-0.50

 fallu

-0.50

CloseOperation

-0.48

styleType

-0.47

❹

-0.47

POSITIVE LOGITS

ǔ

0.62

writeField

0.59

 gesloten

0.51

enschappelijke

0.51

Embeddable

0.50

sible

0.50

 innamor

0.50

PhysRevD

0.50

ísica

0.50

binaan

0.50

Activations Density 0.303%

mentions of scientific or technical terminology

No Comments

No Known Activations