INDEX

Explanations

quotes or direct speech in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Obrigada

-0.67

ERÍA

-0.57

ÁRIO

-0.56

ícone

-0.55

IFORNIA

-0.55

edal

-0.55

 oxid

-0.54

homonymie

-0.53

CCESS

-0.53

 guard

-0.52

POSITIVE LOGITS

1.71

”

1.70

")

1.43

",

1.41

”,

1.33

」

1.31

”)

1.28

".

1.23

)"

1.23

,"

1.23

Activations Density 0.138%

quotes or direct speech in the text

No Comments

No Known Activations