INDEX

Explanations

references to healthy eating and nutrition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

XmlAccessorType

-1.17

$_"

-1.17

 itſelf

-1.14

^(@)

-1.13

 Theſe

-1.02

 myſelf

-1.01

 يتيمه

-1.01

)";

-1.00

 }}"></

-1.00

 ſche

-0.99

POSITIVE LOGITS

 healthy

1.06

healthy

0.82

 tool

0.78

tools

0.76

 Healthy

0.73

↵↵

0.72

 tools

0.70

 healthier

0.69

Healthy

0.67

Tools

0.66

Activations Density 0.072%

references to healthy eating and nutrition

No Comments

No Known Activations