INDEX

Explanations

expressions of happiness or gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 مرئيه

-0.74

XmlAccessType

-0.73

 Meier

-0.72

foria

-0.72

 nakalista

-0.70

Pé

-0.70

apiUrl

-0.68

 Barnett

-0.68

ULTURE

-0.68

uper

-0.67

POSITIVE LOGITS

 glad

3.09

glad

2.53

 Glad

2.52

Glad

2.42

 GLAD

1.99

 froh

1.16

 pleased

1.07

 Gladys

0.99

 Gladstone

0.98

 gladness

0.88

Activations Density 0.063%

expressions of happiness or gratitude

No Comments

No Known Activations

expressions of happiness or gratitude

No Comments

No Known Activations