INDEX

Explanations

discourse markers and punctuation that signify transitions or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 itſelf

-0.77

 himſelf

-0.75

ſelf

-0.73

 myſelf

-0.70

^(@)

-0.69

 Theſe

-0.69

 Majefty

-0.67

oredCriteria

-0.64

astéroïdes

-0.63

 Chriftian

-0.61

POSITIVE LOGITS

 therefore

2.40

 Therefore

2.15

Therefore

2.11

therefore

1.92

Поэтому

1.83

 hence

1.79

 поэтому

1.76

 Поэтому

1.69

 Hence

1.60

因此

1.60

Activations Density 0.609%

discourse markers and punctuation that signify transitions or emphasis

No Comments

No Known Activations