INDEX

Explanations

instances of emphasis or uncertainty in statements

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

 Vikipedi

-0.52

saraba

-0.52

sia

-0.51

جي

-0.51

 dương

-0.51

uvu

-0.50

ic

-0.47

-0.46

ώ

-0.45

POSITIVE LOGITS

 للاسماء

0.98

 betweenstory

0.97

ьаж

0.90

 resourceCulture

0.88

Rüyada

0.83

 Paglinawan

0.82

########.

0.82

脚注の使い方

0.81



0.80

principalColumn

0.77

Activations Density 0.392%

instances of emphasis or uncertainty in statements

No Comments

No Known Activations