INDEX

Explanations

phrases that signify quality, reliability, or suitability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Schaefer

-0.89

 onItemClick

-0.80

ობ

-0.77

 whoſe

-0.76

 Nugent

-0.76

 cremation

-0.72

ᾶ

-0.72

 Lehrer

-0.71

bootstrapcdn

-0.71

 Jefus

-0.71

POSITIVE LOGITS

 well

1.36

 WELL

1.32

 Well

1.29

well

1.25

Well

1.22

 Wells

1.18

Wells

1.12

 wells

1.10

 Welles

1.10

Bien

1.02

Activations Density 0.098%

phrases that signify quality, reliability, or suitability

No Comments

No Known Activations